
# import libraries for data manipulation
import numpy as np
import pandas as pd

# import libraries for data visualization
import matplotlib.pyplot as plt
import seaborn as sns

# set decimal places to 2
pd.set_option('display.float_format', lambda x: '%.2f' % x)


from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive


# read the data
df = pd.read_csv('/content/drive/My Drive/Data Science/GL Projects/foodhub_order.csv')

# returns the first 5 rows
df.head()


df.shape

(1898, 9)


# Use info() to print a concise summary of the DataFrame
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1898 entries, 0 to 1897
Data columns (total 9 columns):
 #   Column                 Non-Null Count  Dtype  
---  ------                 --------------  -----  
 0   order_id               1898 non-null   int64  
 1   customer_id            1898 non-null   int64  
 2   restaurant_name        1898 non-null   object 
 3   cuisine_type           1898 non-null   object 
 4   cost_of_the_order      1898 non-null   float64
 5   day_of_the_week        1898 non-null   object 
 6   rating                 1898 non-null   object 
 7   food_preparation_time  1898 non-null   int64  
 8   delivery_time          1898 non-null   int64  
dtypes: float64(1), int64(4), object(4)
memory usage: 133.6+ KB


df.isnull().sum()

order_id                 0
customer_id              0
restaurant_name          0
cuisine_type             0
cost_of_the_order        0
day_of_the_week          0
rating                   0
food_preparation_time    0
delivery_time            0
dtype: int64


df.describe().T


df[df['rating']=='Not given']['rating'].count()

736


plt.title("Histogram - Food Preparation Time")
plt.xlabel("Food Preparation Time (minutes)")
sns.histplot(data=df, x='food_preparation_time', bins=8, kde=True);


plt.title("Box Plot - Food Preparation Time")
sns.boxplot(data=df, x='food_preparation_time')
plt.xlabel("Food Preparation Time (minutes)");


plt.title("Histogram - Delivery Time")
plt.xlabel("Delivery Time (minutes)")
sns.histplot(data=df, x='delivery_time', kde=True, bins=9);


plt.title("Box Plot - Delivery Time")
sns.boxplot(data=df, x='delivery_time')
plt.xlabel("Delivery Time (minutes)");


plt.title("Histogram - Order Cost")
plt.xlabel("Order Cost (dollars)")
sns.histplot(data=df, x='cost_of_the_order', kde=True, bins=12);


plt.title("Box Plot - Order Cost")
sns.boxplot(data=df, x='cost_of_the_order')
plt.xlabel("Order Cost (dollars)");


plt.figure(figsize=(20,5))
plt.title("Count Plot - Cuisine Type")
sns.countplot(data=df, x='cuisine_type', order = df['cuisine_type'].value_counts().index)
plt.xlabel("Cuisine Type")
plt.ylabel("Count");


plt.title("Count Plot - Day of the Week")
sns.countplot(data=df, x='day_of_the_week')
plt.xlabel("Day of the Week")
plt.ylabel("Count");


plt.title("Count Plot - Ratings")
sns.countplot(data=df, x='rating', order=['Not given','3','4','5'])
plt.xlabel("Rating")
plt.ylabel("Count");


df['restaurant_name'].value_counts().head()

Shake Shack                  219
The Meatball Shop            132
Blue Ribbon Sushi            119
Blue Ribbon Fried Chicken     96
Parm                          68
Name: restaurant_name, dtype: int64


# Checking value_counts of cuisine_type for rows where day_of_the_week is 'Weekend'.

df[df['day_of_the_week']=='Weekend']['cuisine_type'].value_counts().head(1)

American    415
Name: cuisine_type, dtype: int64


# Index based on condition to select rows (orders) where cost is greater than 20 dollars
# Count the number of rows (orders) where cost is greater than 20 dollars with .shape attribute
# Divide by the total number of rows (orders) in the original DataFrame and multiply by 100 to get percent

df[df['cost_of_the_order']>20].shape[0]/df.shape[0]*100

29.24130663856691


# Use .mean() method to find the mean of a column/Series

df['delivery_time'].mean()

24.161749209694417


# Use value_counts method to check the number of orders placed by each unique customer ID in order from greatest to least.

df['customer_id'].value_counts().head(3)

52832    13
47440    10
83287     9
Name: customer_id, dtype: int64


# Check pairplot to look for relationships between numerical variables.

sns.pairplot(data=df[['food_preparation_time','delivery_time','cost_of_the_order']], corner=True);


# Calculate and visualize correlation coefficient for numerical variables using heatmap and .corr method.

sns.heatmap(data=df[['food_preparation_time','delivery_time','cost_of_the_order']].corr(), annot=True);


# Use boxplot to compare cost distribution within different cuisine type categories.

plt.figure(figsize=(20,5))
sns.set(style='darkgrid')
plt.title("Box Plot - Cuisine Type vs. Cost")
sns.boxplot(data=df, x='cuisine_type',y='cost_of_the_order')
plt.xlabel("Cuisine Type")
plt.ylabel("Order Cost (dollars)");


# Use boxplot to compare preparation time distribution within different cuisine type categories.

plt.figure(figsize=(20,5))
sns.set(style='darkgrid')
plt.title("Box Plot - Cuisine Type vs. Preparation Time")
sns.boxplot(data=df, x='cuisine_type',y='food_preparation_time')
plt.xlabel("Cuisine Type")
plt.ylabel("Food Preparation Time (minutes)");


sns.set(style='white')
plt.title("Box Plot - Day of the Week vs. Delivery Time")
sns.boxplot(data=df, x='day_of_the_week', y='delivery_time')
plt.xlabel("Day of the Week")
plt.ylabel("Delivery Time (minutes)");


plt.title("Point Plot - Rating vs. Delivery Time")
sns.pointplot(data=df, x='rating', y='delivery_time', order=['Not given','3','4','5'])
plt.xlabel("Rating")
plt.ylabel("Delivery Time (minutes)");


plt.title("Point Plot - Rating vs. Food Preparation Time")
sns.pointplot(data=df, x='rating', y='food_preparation_time', order=['Not given','3','4','5'])
plt.xlabel("Rating")
plt.ylabel("Preparation Time (minutes)");


plt.title("Point Plot - Rating vs. Order Cost")
sns.pointplot(data=df, x='rating', y='cost_of_the_order', order=['Not given','3','4','5'])
plt.xlabel("Rating")
plt.ylabel("Order Cost (dollars)");


# Create a new DataFrame excluding rows where 'rating' was 'Not given'.

df_ratings = df[df['rating']!='Not given'].copy()


# Change data type of 'rating' column to numeric type in order to perform arithmetic (mean) calculation.

df_ratings['rating'] = df_ratings['rating'].astype(float)


# Use groupby method to create a new DataFrame with restaurants' rating mean and rating count.

df_ratings_agg = df_ratings.groupby('restaurant_name')['rating'].agg(['mean','count']).reset_index()
df_ratings_agg


# Use logical indexing to display a list of the restaurants with mean rating above 4 and rating count more than 50.

df_ratings_agg[(df_ratings_agg['mean']>4)&(df_ratings_agg['count']>50)]['restaurant_name'].tolist()

['Blue Ribbon Fried Chicken',
 'Blue Ribbon Sushi',
 'Shake Shack',
 'The Meatball Shop']


# Find the sum of 'cost_of_the_order' where cost is greater than 20 and multiply by 0.25 to get 25%.
# Find the sum of 'cost_of_the_order' where cost is greater than 5 and less than or equal to 20. Mutiply by 0.15 to get 15%.
# Add the two together to get net revenue across all orders.

df[df['cost_of_the_order']>20]['cost_of_the_order'].sum()*.25 + df[(df['cost_of_the_order']>5)&(df['cost_of_the_order']<=20)]['cost_of_the_order'].sum()*.15

6166.303


# Create a new column called 'total_time' which is the sum of food_preparation_time plus delivery_time.
# Use conditional indexing with .shape method to count the number of rows where total_time is greater than 60. Divide by original number of rows & multiply by 100 to get percent.

df['total_time'] = df['food_preparation_time'] + df['delivery_time']
df[df['total_time']>60].shape[0]/df.shape[0]*100

10.537407797681771


# Find the difference between the mean delivery time on weekdays vs. weekends using logical indexing.

df[df['day_of_the_week']=='Weekday']['delivery_time'].mean()-df[df['day_of_the_week']=='Weekend']['delivery_time'].mean()

5.870014357297798


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
import scipy.stats as stats


from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive


data = pd.read_csv('/content/drive/My Drive/Data Science/GL Projects/abtest.csv')


# Display the first 5 and last 5 rows of the data

data


# Use .shape attribute to return number of rows & columns in the data

print(f'There are {data.shape[0]} rows & {data.shape[1]} columns.')

There are 100 rows & 6 columns.


# Use .describe() method to display statistical summary of numerical variable (drop user_id column as it is not numerical)

data.describe().T.drop('user_id')


# Use include='object' parameter to display summary of categorical variables

data.describe(include='object').T


# Use .info() method to check non-null counts and column datatypes

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 100 entries, 0 to 99
Data columns (total 6 columns):
#   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
0   user_id                 100 non-null    int64  
1   group                   100 non-null    object 
2   landing_page            100 non-null    object 
3   time_spent_on_the_page  100 non-null    float64
4   converted               100 non-null    object 
5   language_preferred      100 non-null    object 
dtypes: float64(1), int64(1), object(4)
memory usage: 4.8+ KB


# Use .isnull() and .sum() methods to verify there are no missing (null) values

data.isnull().sum()

user_id                   0
group                     0
landing_page              0
time_spent_on_the_page    0
converted                 0
language_preferred        0
dtype: int64


# Use .duplicated() and .sum() methods to check for duplicated data

data.duplicated().sum()

0


# Use histogram to visualize numerical variable

sns.set_palette("Set1")
sns.histplot(data, x='time_spent_on_the_page', kde=True)
plt.title('Histogram: Time Spent on Page')
plt.xlabel('Time Spent on Page');


# Use boxplot to visualize numerical variable

sns.boxplot(data=data, x='time_spent_on_the_page')
plt.title('Box Plot: Time Spent on Page')
plt.xlabel('Time Spent on Page');


# Use countplot to visualize categorical variables

sns.countplot(data=data, x='group')
plt.title('Countplot: Group')
plt.xlabel('Group')
plt.ylabel('Count');


sns.countplot(data=data, x='landing_page')
plt.title('Countplot: Landing Page')
plt.xlabel('Landing Page')
plt.ylabel('Count');


sns.countplot(data=data, x='converted')
plt.title('Countplot: Converted')
plt.xlabel('Converted')
plt.ylabel('Count');


sns.countplot(data=data.sort_values('language_preferred'), x='language_preferred')
plt.title('Countplot: Language Preferred')
plt.xlabel('Language Preferred')
plt.ylabel('Count');


sns.boxplot(data=data, x='landing_page', y='time_spent_on_the_page')
plt.title('Box Plot: Time Spent on Page for Old vs. New')
plt.xlabel('Landing Page')
plt.ylabel('Time Spent on Page');


sns.boxplot(data=data, x='converted', y='time_spent_on_the_page')
plt.title('Box Plot: Time Spent on Page for Conversion')
plt.xlabel('Converted')
plt.ylabel('Time Spent on Page');


sns.boxplot(data=data, x='language_preferred', y='time_spent_on_the_page')
plt.title('Box Plot: Time Spent on Page with Preferred Language')
plt.xlabel('Preferred Language')
plt.ylabel('Time Spent on Page');


sns.countplot(data=data, x='landing_page', hue='converted')
plt.title('Count Plot: Conversion based on Landing Page')
plt.xlabel('Landing Page')
plt.ylabel('Count');


sns.countplot(data=data, x='language_preferred', hue='converted')
plt.title('Count Plot: Conversion based on Language')
plt.xlabel('Preferred Language')
plt.ylabel('Count');


sns.boxplot(data=data, x='landing_page', y='time_spent_on_the_page')
plt.title('Box Plot: Time Spent on Old vs. New Page')
plt.xlabel('Landing Page')
plt.ylabel('Time Spent on Page');


# Create new DataFrames to separate data for old landing page vs. new landing page. Calculate mean and standard deviation for each.

data_old = data[data['landing_page']=='old'].reset_index(drop=True)
data_new = data[data['landing_page']=='new'].reset_index(drop=True)

print(f'The average time spent on the old landing page is {round(data_old["time_spent_on_the_page"].mean(),2)} minutes with standard deviation of {round(data_old["time_spent_on_the_page"].std(),2)} minutes')
print(f'The average time spent on the new landing page is {round(data_new["time_spent_on_the_page"].mean(),2)} minutes with standard deviation of {round(data_new["time_spent_on_the_page"].std(),2)} minutes')

The average time spent on the old landing page is 4.53 minutes with standard deviation of 2.58 minutes
The average time spent on the new landing page is 6.22 minutes with standard deviation of 1.82 minutes


# Use independent t-test function with equal_var=False to indicate that sample standard deviations are not equal.

from scipy.stats import ttest_ind
test_stat, p_value = ttest_ind(data_new['time_spent_on_the_page'],data_old['time_spent_on_the_page'], equal_var=False, alternative='greater')
print(f'The p-value is {p_value}')

The p-value is 0.0001392381225166549


# Create a new DataFrame to count conversions

conversions = pd.DataFrame({
  'Page':['New page','Old page'],
  'Converted':
    [data_new['converted'][data_new['converted']=='yes'].count(),
     data_old['converted'][data_old['converted']=='yes'].count()],
  'Not converted':
    [data_new['converted'][data_new['converted']=='no'].count(),
     data_old['converted'][data_old['converted']=='no'].count()],
  'Sample size':[data_new.shape[0],data_old.shape[0]]})

conversions


# Add a new column to calculate conversion rate (number of users converted out of each sample)

conversions['Conversion Rate'] = conversions['Converted']/conversions['Sample size']
conversions


# Use a bar plot to visualize difference between conversion rate for old page vs. new page

sns.catplot(data=conversions, x='Page', y='Conversion Rate', kind='bar')
plt.title('Bar Plot: Conversion Rate for New Page vs. Old Page');


# Use NumPy arrays of conversion counts and number of observations in each category to execute the proportions_ztest function

conversion_count = np.array(conversions['Converted'])
nobs = np.array(conversions['Sample size'])

from statsmodels.stats.proportion import proportions_ztest
test_stat, p_value = proportions_ztest(conversion_count, nobs)
print(f'The p-value is {p_value}')

The p-value is 0.016052616408112556


# Create new DataFrames to separate data by preferred language

data_eng = data[data['language_preferred']=='English']
data_fren = data[data['language_preferred']=='French']
data_span = data[data['language_preferred']=='Spanish']


# Create a contingency table for conversion and preferred language

lang_table = pd.DataFrame({
  'Language':['English','French','Spanish'],
  'Converted':
    [data_eng['converted'][data_eng['converted']=='yes'].count(),
     data_fren['converted'][data_fren['converted']=='yes'].count(),
     data_span['converted'][data_span['converted']=='yes'].count()],
  'Not converted':
    [data_eng['converted'][data_eng['converted']=='no'].count(),
     data_fren['converted'][data_fren['converted']=='no'].count(),
     data_span['converted'][data_span['converted']=='no'].count()],
  'Sample size':[data_eng.shape[0],data_fren.shape[0],data_span.shape[0]]})

lang_table


# Add a column with the conversion rate for each language

lang_table['Conversion rate'] = round(lang_table['Converted']/lang_table['Sample size'],2)
lang_table


# Use a bar plot to visualize conversion rates for each language

sns.catplot(data=lang_table.sort_values('Conversion rate'), x='Language', y='Conversion rate', kind='bar')
plt.title('Bar Plot: Conversion Rate for Preferred Languages');


# Use chi2_contingency function to find the p-value from the contingency table

from scipy.stats import chi2_contingency
chi, p_value, dof, expected = chi2_contingency(lang_table.drop(['Language','Sample size','Conversion rate'], axis = 1))
print(f'The p-value is {p_value}')

The p-value is 0.2129888748754345


# Use indexing of separate DataFrames by language with .mean() method to find average time spent on the new landing page

eng_time = round(data_eng[data_eng["landing_page"]=="new"]["time_spent_on_the_page"].mean(),2)
fren_time = round(data_fren[data_fren["landing_page"]=="new"]["time_spent_on_the_page"].mean(),2)
span_time = round(data_span[data_span["landing_page"]=="new"]["time_spent_on_the_page"].mean(),2)

print(f'The mean time spent on the new page by users preferring English was {eng_time} minutes')
print(f'The mean time spent on the new page by users preferring French was {fren_time} minutes')
print(f'The mean time spent on the new page by users preferring Spanish was {span_time} minutes')

The mean time spent on the new page by users preferring English was 6.66 minutes
The mean time spent on the new page by users preferring French was 6.2 minutes
The mean time spent on the new page by users preferring Spanish was 5.84 minutes


# Create a dataframe with mean time spent on new page by preferred language for visualization

time_df = pd.DataFrame({'Language':['English','French','Spanish'],'Mean Time':[eng_time,fren_time,span_time]})
time_df


# Use a bar plot to visualize mean time spent on new page for each language

sns.catplot(data=time_df.sort_values('Mean Time'), x='Language', y='Mean Time', kind='bar')
plt.title('Bar Plot: Mean Time Spent on New Page')
plt.ylabel('Mean time (minutes)');


w, p_value = stats.shapiro(data_new['time_spent_on_the_page'])
print(f'The p-value is {p_value}')

The p-value is 0.8040016293525696


from scipy.stats import levene
statistic, p_value = levene(
data_new['time_spent_on_the_page'][data_new['language_preferred']=="English"],
data_new['time_spent_on_the_page'][data_new['language_preferred']=="French"],
data_new['time_spent_on_the_page'][data_new['language_preferred']=="Spanish"])

print(f"The p-value for Levene's test is {p_value}")

The p-value for Levene's test is 0.46711357711340173


# Perform the ANOVA test using f_oneway function

from scipy.stats import f_oneway
test_stat, p_value = f_oneway(
data_new.loc[data_new['language_preferred'] == 'English', 'time_spent_on_the_page'],
data_new.loc[data_new['language_preferred'] == 'French', 'time_spent_on_the_page'],
data_new.loc[data_new['language_preferred'] == 'Spanish', 'time_spent_on_the_page'])

print(f'The p-value for the ANOVA test is {p_value}')

The p-value for the ANOVA test is 0.43204138694325955


# Import libraries for data manipulation.
import pandas as pd
import numpy as np

# Import libraries for data visualization.
import matplotlib.pyplot as plt
import seaborn as sns

# Import libraries for linear regression.
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
import statsmodels.api as sm
from statsmodels.stats.outliers_influence import variance_inflation_factor
import pylab
import scipy.stats as stats
import statsmodels.stats.api as sms
from statsmodels.compat import lzip

# set decimal places to 2
pd.set_option('display.float_format', lambda x: '%.2f' % x)


from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive


data = pd.read_csv('/content/drive/My Drive/Data Science/Current/used_device_data.csv')


# Use .shape attribute to display the number of rows & columns in the data set.

data.shape

(3454, 15)


# Display a sample of 5 rows from the data set to get a general idea of the information & make sure it is loaded properly.

data.sample(5)


# Use .info() method to check the non-null counts and data types of each column.

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3454 entries, 0 to 3453
Data columns (total 15 columns):
 #   Column                 Non-Null Count  Dtype  
---  ------                 --------------  -----  
 0   brand_name             3454 non-null   object 
 1   os                     3454 non-null   object 
 2   screen_size            3454 non-null   float64
 3   4g                     3454 non-null   object 
 4   5g                     3454 non-null   object 
 5   main_camera_mp         3275 non-null   float64
 6   selfie_camera_mp       3452 non-null   float64
 7   int_memory             3450 non-null   float64
 8   ram                    3450 non-null   float64
 9   battery                3448 non-null   float64
 10  weight                 3447 non-null   float64
 11  release_year           3454 non-null   int64  
 12  days_used              3454 non-null   int64  
 13  normalized_used_price  3454 non-null   float64
 14  normalized_new_price   3454 non-null   float64
dtypes: float64(9), int64(2), object(4)
memory usage: 404.9+ KB


# Check the statistical summary for the numeric columns, dropping release_year as it is not numeric.

data.describe().T.drop('release_year')


# Check the statistical summary for the categorical variables.

data.describe(include='object').T


# Check for duplicated values.

data.duplicated().sum()

0


# Use a histogram to visualize the distribution of a numeric variable.

plt.title('Histogram: Normalized Used Price')
plt.xlabel('Normalized Used Price (euros)')
sns.histplot(data, x='normalized_used_price',kde=True);


# Use a boxplot to visualize distribution and outliers.

plt.title('Boxplot: Normalized Used Price')
sns.boxplot(data=data,x='normalized_used_price')
plt.xlabel('Normalized Used Price (euros)');


# Use countplot to visualize the distribution of operating systems.

plt.title('Countplot: Operating Systems')
sns.countplot(data=data, x='os', order=data['os'].value_counts().reset_index()['index'].tolist())
plt.xlabel('OS')
plt.ylabel('Count');


# Divide the number of rows where os=Android by the total number of rows & multiply by 100 to get percent.

data[data['os']=='Android'].shape[0]/data.shape[0]*100

93.05153445280834


# Use boxplot to visualize variations in RAM across different brands.

plt.figure(figsize=(20, 5))
plt.title('Boxplot: RAM by Brand')
sns.boxplot(data=data, x="brand_name", y="ram", order=data.groupby(['brand_name'])['ram'].median().reset_index().sort_values('ram')['brand_name'].tolist())
plt.xticks(rotation=45)
plt.xlabel('Brand name')
plt.ylabel('RAM (GB)');


# Use .groupby() method to determine which brands have the highest and lowest average RAM.

brand_ram = data.groupby(['brand_name'])['ram'].mean().reset_index()
brand_ram = brand_ram.sort_values('ram', ascending=False)
with pd.option_context('display.max_rows',6):
    print(brand_ram)

   brand_name  ram
22    OnePlus 6.36
23       Oppo 4.96
30       Vivo 4.76
..        ...  ...
12    Infinix 2.60
21      Nokia 2.42
5      Celkon 1.61

[34 rows x 2 columns]


# Use a scatterplot with best-fit line to visualize the relationship between battery capacity and weight for high-capacity batteries.

sns.lmplot(data=data[data['battery']>4500],x='battery',y='weight')
plt.title('Scatterplot: Battery Capacity vs. Weight')
plt.xlabel('Battery capacity (mAh)')
plt.ylabel('Weight (grams)');


# Calculate the percentage of phones with battery capacity >4500 mAh.

data[data['battery']>4500].shape[0]/data.shape[0]*100

9.872611464968154


# Visualize the variations in weight for phones with high capacity batteries across different brands.

plt.figure(figsize=(20,5))
sns.boxplot(data=data[data['battery']>4500], x='brand_name', y='weight', order=data[data['battery']>4500].groupby(['brand_name'])['weight'].median().reset_index().sort_values('weight')['brand_name'].tolist())
plt.xticks(rotation=45)
plt.title('Boxplot: Weight by Brand')
plt.xlabel('Brand')
plt.ylabel('Weight (grams)');


# Create a new DataFrame to add a column converting screen size from centimeters to inches. Index by screen size >6 inches to get percentage of used phones with screen size >6 inches.

data_in = data.copy()
data_in['screen_in'] = data_in['screen_size']*0.393701
data_in[data_in['screen_in']>6].shape[0]/data.shape[0]*100

35.552982049797336


# Use a countplot to visualize the number of large-screen phones available across different brands.

plt.figure(figsize=(20,5))
sns.countplot(data=data_in[data_in['screen_in']>6], x='brand_name', order=data_in[data_in['screen_in']>6]['brand_name'].value_counts().reset_index()['index'].tolist())
plt.xticks(rotation=45)
plt.title('Countplot: Large Screens by Brand')
plt.xlabel('Brand')
plt.ylabel('Count (screen size > 6 in)');


# Create a new DataFrame to store the count and percentage of phones with screen size over 6 inches by brand.

large = data_in[data_in['screen_in']>6]['brand_name'].value_counts().rename('large').reset_index()
totals = data['brand_name'].value_counts().rename('total').reset_index()
scrn_pct = pd.merge(large,totals)
scrn_pct.rename(columns={'index':'brand'}, inplace=True)
scrn_pct['pct_large'] = scrn_pct['large']/scrn_pct['total']*100
scrn_pct = scrn_pct.sort_values(by='pct_large', ascending=False)
with pd.option_context('display.max_rows',10):
    print(scrn_pct)

        brand  large  total  pct_large
11     Realme     41     41     100.00
22    Infinix     10     10     100.00
19    OnePlus     16     22      72.73
3        Vivo     82    117      70.09
0      Huawei    157    251      62.55
..        ...    ...    ...        ...
25       XOLO      4     49       8.16
28    Karbonn      2     29       6.90
29      Spice      2     30       6.67
26  Panasonic      3     47       6.38
30  Microsoft      1     22       4.55

[31 rows x 4 columns]


# Use .shape attribute and logical indexing to calculate percentage of phones with >8 MP selfie cameras.

data[data['selfie_camera_mp']>8].shape[0]/data.shape[0]*100

18.963520555877245


# Use a countplot to visualize the number of phones available across different brands with high selfie camera MP.

plt.figure(figsize=(20,5))
sns.countplot(data=data[data['selfie_camera_mp']>8], x='brand_name', order=data[data['selfie_camera_mp']>8]['brand_name'].value_counts().reset_index()['index'].tolist())
plt.title('Countplot: High Selfie Camera MP by Brand')
plt.xlabel('Brand')
plt.ylabel('Count (selfie camera MP > 8)')
plt.xticks(rotation=45);


# Create a new DataFrame to store the count and percentage of phones with selfie camera MP >8 by brand.

high = data[data['selfie_camera_mp']>8]['brand_name'].value_counts().rename('over_8').reset_index()
total = data['brand_name'].value_counts().rename('total').reset_index()
sMP_pct = pd.merge(high,total)
sMP_pct.rename(columns={'index':'brand'}, inplace=True)
sMP_pct['pct_over8'] = sMP_pct['over_8']/sMP_pct['total']*100
sMP_pct = sMP_pct.sort_values(by='pct_over8', ascending=False)
with pd.option_context('display.max_rows',10):
    print(sMP_pct)

        brand  over_8  total  pct_over8
13    OnePlus      18     22      81.82
1        Vivo      78    117      66.67
2        Oppo      75    129      58.14
3      Xiaomi      63    132      47.73
12     Realme      18     41      43.90
..        ...     ...    ...        ...
6      Others      34    502       6.77
17       Asus       6    122       4.92
23  Panasonic       2     47       4.26
24       Acer       1     51       1.96
22   Micromax       2    117       1.71

[25 rows x 4 columns]


# Use correlation heatmap to visualize which variables have the highest correlation with normalized used price.

plt.figure(figsize=(12,7))
sns.heatmap(data=data.drop('release_year',axis=1).corr().sort_values('normalized_used_price',ascending=False), annot=True)
plt.title('Heatmap: Correlation between numeric variables');


# Display pairplot to visualize the relationships between the variables most correlated with normalized used price.

sns.pairplot(data=data[['normalized_used_price','normalized_new_price','battery','selfie_camera_mp','screen_size']]);


# Use a histogram to visualize the distribution of screen size (numeric variable).

plt.figure(figsize=(20,5))
sns.histplot(data=data, x='screen_size', kde=True, bins=25)
plt.title('Histogram: Screen Size')
plt.xlabel('Screen Size (cm)');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
sns.boxplot(data=data, x='screen_size')
plt.title('Boxplot: Screen Size')
plt.xlabel('Screen Size (cm)');


# Use histogram to visualize the distribution of main camera MP.

plt.figure(figsize=(20,5))
sns.histplot(data=data, x='main_camera_mp', kde=True)
plt.title('Histogram: Main Camera MP')
plt.xlabel('Main Camera MP');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
sns.boxplot(data=data, x='main_camera_mp')
plt.title('Boxplot: Main Camera MP')
plt.xlabel('Main Camera MP');


# Use histogram to check distribution of selfie camera MP.

plt.figure(figsize=(20,5))
plt.title('Histogram: Selfie Camera MP')
sns.histplot(data=data, x='selfie_camera_mp', kde=True, bins=10)
plt.xlabel('Selfie Camera MP');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
plt.title('Boxplot: Selfie Camera MP')
sns.boxplot(data=data, x='selfie_camera_mp')
plt.xlabel('Selfie Camera MP');


# Use histogram to visualize distribution of internal memory.

plt.figure(figsize=(20,5))
plt.title('Histogram: Internal Memory')
sns.histplot(data=data, x='int_memory', kde=True, bins=25)
plt.xlabel('Internal Memory (GB)');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
plt.title('Boxplot: Internal Memory')
sns.boxplot(data=data, x='int_memory')
plt.xlabel('Internal Memory (GB)');


# Use countplot to visualize internal memory as values are semi-discrete.

plt.figure(figsize=(20,5))
sns.countplot(data=data, x='int_memory')
plt.title('Countplot: Internal Memory')
plt.xlabel('Internal Memory (GB)')
plt.ylabel('Count');


# Use histogram to visualize the distribution of RAM.

plt.figure(figsize=(20,5))
sns.histplot(data=data, x='ram',kde=True)
plt.title('Histogram: RAM')
plt.xlabel('RAM (GB)');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
sns.boxplot(data=data, x='ram')
plt.title('Boxplot: RAM')
plt.xlabel('RAM (GB)');


# Use countplot to visualize RAM as values are semi-discrete.

plt.figure(figsize=(20,5))
sns.countplot(data=data, x='ram')
plt.title('Countplot: RAM')
plt.xlabel('RAM (GB)')
plt.ylabel('Count');


# Use histogram to visualize the distribution of battery capacity.

plt.figure(figsize=(20,5))
sns.histplot(data=data, x='battery', kde=True)
plt.title('Histogram: Battery Capacity')
plt.xlabel('Battery Capacity (mAh)');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
sns.boxplot(data=data, x='battery')
plt.title('Boxplot: Battery Capacity')
plt.xlabel('Battery Capacity (mAh)');


# Use histogram to visualize the distribution of weight.

plt.figure(figsize=(20,5))
sns.histplot(data=data, x='weight', kde=True)
plt.title('Histogram: Weight')
plt.xlabel('Weight (grams)');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
sns.boxplot(data=data, x='weight')
plt.title('Boxplot: Weight')
plt.xlabel('Weight (grams)');


# Use histogram to visualize the distribution of days used.

plt.figure(figsize=(20,5))
sns.histplot(data=data, x='days_used', kde=True)
plt.title('Histogram: Days Used')
plt.xlabel('Days Used');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
sns.boxplot(data=data, x='days_used')
plt.title('Boxplot: Days Used')
plt.xlabel('Days Used');


# Use histogram to visualize the distribution of normalized new price.

plt.figure(figsize=(20,5))
sns.histplot(data=data, x='normalized_new_price', kde=True, bins=30)
plt.title('Histogram: Normalized New Price')
plt.xlabel('Normalized New Price (euros)');


# Use boxplot to further visualize distribution and outliers.

plt.figure(figsize=(20,5))
sns.boxplot(data=data, x='normalized_new_price')
plt.title('Boxplot: Normalized New Price')
plt.xlabel('Normalized New Price (euros)');


# Use countplot to visualize the distribution of release year.

plt.figure(figsize=(20,5))
sns.countplot(data=data, x='release_year')
plt.title('Countplot: Release Year')
plt.xlabel('Release Year')
plt.ylabel('Count');


# Use a lineplot to visualize the change in normalized used price based on release year.

plt.figure(figsize=(20,5))
sns.lineplot(data=data, x='release_year',y='normalized_used_price')
plt.title('Lineplot: Normalized Used Price by Release Year')
plt.xlabel('Release Year')
plt.ylabel('Normalized Used Price (euros)');


# Use countplot to visualize the distribution of brand names.

plt.figure(figsize=(20,5))
sns.countplot(data=data, x='brand_name', order=data['brand_name'].value_counts().reset_index()['index'].tolist())
plt.xticks(rotation=45)
plt.title('Countplot: Brand Name')
plt.xlabel('Brand Name')
plt.ylabel('Count');


# Use countplot to visualize the distribution of 4G devices.

sns.countplot(data=data, x='4g')
plt.title('Countplot: 4G')
plt.xlabel('4G')
plt.ylabel('Count');


# Use boxplot to visualize the variation in normalized used price between phones with and without 4G.

sns.boxplot(data=data, x='4g', y='normalized_used_price')
plt.title('Boxplot: Normalized Used Price by 4G')
plt.xlabel('4G')
plt.ylabel('Normalized Used Price (euros)');


# Use countplot to visualize the distribution of 5G devices.

sns.countplot(data=data, x='5g', order=['yes','no'])
plt.title('Countplot: 5G')
plt.xlabel('5G')
plt.ylabel('Count');


# Use boxplot to visualize the variation in normalized used price between phones with and without 5G.

sns.boxplot(data=data, x='5g', y='normalized_used_price', order=['yes','no'])
plt.title('Boxplot: Normalized Used Price by 5G')
plt.xlabel('5G')
plt.ylabel('Normalized Used Price (euros)');


# Display the count and percentage of missing values in each column. 

pd.DataFrame({'Count':data.isnull().sum()[data.isnull().sum()>0],'Percentage':(data.isnull().sum()[data.isnull().sum()>0]/data.shape[0])*100})


# Create a copy of the data to deal with missing values.

data2 = data.copy()


# Replace null values for main camera MP with the median main camera MP for phones of the same brand.

data2['main_camera_mp'] = data2['main_camera_mp'].fillna(value = data2.groupby(['brand_name','release_year'])['main_camera_mp'].transform('median'))


# Check for remaining null vallues in the main camera MP column.

data2.loc[data2['main_camera_mp'].isnull()==True]


# Some of the values couldn't be imputed by brand name and release year, so they will be imputed by brand name alone.

data2['main_camera_mp'] = data2['main_camera_mp'].fillna(value = data2.groupby(['brand_name'])['main_camera_mp'].transform('median'))


# Check for remaining null vallues in the main camera MP column.

data2.loc[data2['main_camera_mp'].isnull()==True]


# None of the Infinix brand phones have values for main camera MP, so these values cannot be imputed by brand. 
# Instead the values can be imputed by release year.

data2['main_camera_mp'] = data2['main_camera_mp'].fillna(value = data2.groupby(['release_year'])['main_camera_mp'].transform('median'))


# Verify that there are no remaining null values in the main camera MP column.

data2['main_camera_mp'].isnull().sum()

0


# Impute the remaining null values using median values grouped by brand & release year.

data2['selfie_camera_mp'] = data2['selfie_camera_mp'].fillna(value = data2.groupby(['brand_name','release_year'])['selfie_camera_mp'].transform('median'))
data2['int_memory'] = data2['int_memory'].fillna(value = data2.groupby(['brand_name','release_year'])['int_memory'].transform('median'))
data2['ram'] = data2['ram'].fillna(value = data2.groupby(['brand_name','release_year'])['ram'].transform('median'))
data2['battery'] = data2['battery'].fillna(value = data2.groupby(['brand_name','release_year'])['battery'].transform('median'))
data2['weight'] = data2['weight'].fillna(value = data2.groupby(['brand_name','release_year'])['weight'].transform('median'))


# Check if there are any remaining null values.

data2.isnull().sum()

brand_name               0
os                       0
screen_size              0
4g                       0
5g                       0
main_camera_mp           0
selfie_camera_mp         2
int_memory               0
ram                      0
battery                  6
weight                   7
release_year             0
days_used                0
normalized_used_price    0
normalized_new_price     0
dtype: int64


# The remaining null values can be imputed by brand alone.

data2['selfie_camera_mp'] = data2['selfie_camera_mp'].fillna(value = data2.groupby(['brand_name',])['selfie_camera_mp'].transform('median'))
data2['battery'] = data2['battery'].fillna(value = data2.groupby(['brand_name'])['battery'].transform('median'))
data2['weight'] = data2['weight'].fillna(value = data2.groupby(['brand_name'])['weight'].transform('median'))


# Verify that there are no remaining null values.

data2.isnull().sum()

brand_name               0
os                       0
screen_size              0
4g                       0
5g                       0
main_camera_mp           0
selfie_camera_mp         0
int_memory               0
ram                      0
battery                  0
weight                   0
release_year             0
days_used                0
normalized_used_price    0
normalized_new_price     0
dtype: int64


# Replace release_year with a new column for years_since_release to allow more meaningful statistical analysis.

data2['years_since_release'] = 2022 - data2['release_year']
data2.drop('release_year', axis=1, inplace=True)


# Check the statistical summary of the new column.

data2['years_since_release'].describe()

count   3454.00
mean       6.03
std        2.30
min        2.00
25%        4.00
50%        6.50
75%        8.00
max        9.00
Name: years_since_release, dtype: float64


# Create a variable for the numeric columns.

numeric_columns = ['screen_size', 'main_camera_mp', 'selfie_camera_mp', 'int_memory', 'ram', 'battery', 'weight', 'days_used', 'normalized_used_price', 'normalized_new_price','years_since_release']


# Display boxplots for each numeric variable to visualize outliers.

plt.figure(figsize=(20,10))

for i, variable in enumerate(numeric_columns):
    plt.subplot(3, 4, i + 1)
    plt.boxplot(data2[variable], whis=1.5)
    plt.tight_layout()
    plt.title(variable)


# Double-check the statistical summary to determine if maximum and minimum values are reasonable based on domain knowledge.

data2.describe().T


# Compare the statistical summary for the processed data set to that of the original data set.

data2.describe().T.drop(['days_used','normalized_new_price','normalized_used_price','screen_size','years_since_release']) / data.describe().T.drop(['days_used','normalized_new_price','normalized_used_price','screen_size','release_year'])


# Use histogram to visualize the distribution of main camera MP for the original data.

plt.figure(figsize=(20,5))
sns.histplot(data=data, x='main_camera_mp', kde=True)
plt.title('Histogram: Main Camera MP')
plt.xlabel('Main Camera MP');


# Use histogram to visualize the distribution of main camera MP for the processed data.

plt.figure(figsize=(20,5))
sns.histplot(data=data2, x='main_camera_mp', kde=True)
plt.title('Histogram: Main Camera MP')
plt.xlabel('Main Camera MP');


# Use boxplot to further visualize distribution and outliers for the original data set.

plt.figure(figsize=(20,5))
sns.boxplot(data=data, x='main_camera_mp')
plt.title('Boxplot: Main Camera MP')
plt.xlabel('Main Camera MP');


# Use boxplot to further visualize distribution and outliers for the processed data.

plt.figure(figsize=(20,5))
sns.boxplot(data=data2, x='main_camera_mp')
plt.title('Boxplot: Main Camera MP')
plt.xlabel('Main Camera MP');


# Define X and y variables in order to predict used phone price.

X = data2.drop(['normalized_used_price'], axis=1)
y = data2['normalized_used_price']

print(X.head())
print()
print(y.head())

  brand_name       os  screen_size   4g   5g  main_camera_mp  \
0      Honor  Android        14.50  yes   no           13.00   
1      Honor  Android        17.30  yes  yes           13.00   
2      Honor  Android        16.69  yes  yes           13.00   
3      Honor  Android        25.50  yes  yes           13.00   
4      Honor  Android        15.32  yes   no           13.00   

   selfie_camera_mp  int_memory  ram  battery  weight  days_used  \
0              5.00       64.00 3.00  3020.00  146.00        127   
1             16.00      128.00 8.00  4300.00  213.00        325   
2              8.00      128.00 8.00  4200.00  213.00        162   
3              8.00       64.00 6.00  7250.00  480.00        345   
4              8.00       64.00 3.00  5000.00  185.00        293   

   normalized_new_price  years_since_release  
0                  4.72                    2  
1                  5.52                    2  
2                  5.88                    2  
3                  5.63                    2  
4                  4.95                    2  

0   4.31
1   5.16
2   5.11
3   5.14
4   4.39
Name: normalized_used_price, dtype: float64


# Add the intercept.

X = sm.add_constant(X)

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/tsatools.py:142: FutureWarning: In a future version of pandas all arguments of concat except for the argument 'objs' will be keyword-only
  x = pd.concat(x[::order], 1)


# Create dummy variables for categorical (string/object) columns.

X = pd.get_dummies(
    X,
    columns=X.select_dtypes(include=['object', 'category']).columns.tolist(),
    drop_first=True,
)
X.head()


# Split the data into training and testing sets in a 70:30 ratio.

x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)


print("Number of rows in train data =", x_train.shape[0])
print("Number of rows in test data =", x_test.shape[0])

Number of rows in train data = 2417
Number of rows in test data = 1037


# Start by creating a model that incorporates every single independent variable in the data set.

olsmodel = sm.OLS(y_train, x_train).fit()
print(olsmodel.summary())

                              OLS Regression Results                             
=================================================================================
Dep. Variable:     normalized_used_price   R-squared:                       0.845
Model:                               OLS   Adj. R-squared:                  0.842
Method:                    Least Squares   F-statistic:                     268.7
Date:                   Fri, 07 Oct 2022   Prob (F-statistic):               0.00
Time:                           00:24:05   Log-Likelihood:                 123.85
No. Observations:                   2417   AIC:                            -149.7
Df Residuals:                       2368   BIC:                             134.0
Df Model:                             48                                         
Covariance Type:               nonrobust                                         
=========================================================================================
                            coef    std err          t      P>|t|      [0.025      0.975]
-----------------------------------------------------------------------------------------
const                     1.3393      0.072     18.563      0.000       1.198       1.481
screen_size               0.0244      0.003      7.163      0.000       0.018       0.031
main_camera_mp            0.0208      0.002     13.848      0.000       0.018       0.024
selfie_camera_mp          0.0135      0.001     11.997      0.000       0.011       0.016
int_memory                0.0001   6.97e-05      1.651      0.099   -2.16e-05       0.000
ram                       0.0230      0.005      4.451      0.000       0.013       0.033
battery               -1.689e-05   7.27e-06     -2.321      0.020   -3.12e-05   -2.62e-06
weight                    0.0010      0.000      7.480      0.000       0.001       0.001
days_used              4.216e-05   3.09e-05      1.366      0.172   -1.84e-05       0.000
normalized_new_price      0.4311      0.012     35.147      0.000       0.407       0.455
years_since_release      -0.0237      0.005     -5.193      0.000      -0.033      -0.015
brand_name_Alcatel        0.0154      0.048      0.323      0.747      -0.078       0.109
brand_name_Apple         -0.0038      0.147     -0.026      0.980      -0.292       0.285
brand_name_Asus           0.0151      0.048      0.314      0.753      -0.079       0.109
brand_name_BlackBerry    -0.0300      0.070     -0.427      0.669      -0.168       0.108
brand_name_Celkon        -0.0468      0.066     -0.707      0.480      -0.177       0.083
brand_name_Coolpad        0.0209      0.073      0.287      0.774      -0.122       0.164
brand_name_Gionee         0.0448      0.058      0.775      0.438      -0.068       0.158
brand_name_Google        -0.0326      0.085     -0.385      0.700      -0.199       0.133
brand_name_HTC           -0.0130      0.048     -0.270      0.787      -0.108       0.081
brand_name_Honor          0.0317      0.049      0.644      0.520      -0.065       0.128
brand_name_Huawei        -0.0020      0.044     -0.046      0.964      -0.089       0.085
brand_name_Infinix        0.0592      0.093      0.634      0.526      -0.124       0.242
brand_name_Karbonn        0.0943      0.067      1.405      0.160      -0.037       0.226
brand_name_LG            -0.0132      0.045     -0.291      0.771      -0.102       0.076
brand_name_Lava           0.0332      0.062      0.533      0.594      -0.089       0.155
brand_name_Lenovo         0.0454      0.045      1.004      0.316      -0.043       0.134
brand_name_Meizu         -0.0129      0.056     -0.230      0.818      -0.123       0.097
brand_name_Micromax      -0.0337      0.048     -0.704      0.481      -0.128       0.060
brand_name_Microsoft      0.0952      0.088      1.078      0.281      -0.078       0.268
brand_name_Motorola      -0.0112      0.050     -0.226      0.821      -0.109       0.086
brand_name_Nokia          0.0719      0.052      1.387      0.166      -0.030       0.174
brand_name_OnePlus        0.0709      0.077      0.916      0.360      -0.081       0.223
brand_name_Oppo           0.0124      0.048      0.261      0.794      -0.081       0.106
brand_name_Others        -0.0080      0.042     -0.190      0.849      -0.091       0.075
brand_name_Panasonic      0.0563      0.056      1.008      0.314      -0.053       0.166
brand_name_Realme         0.0319      0.062      0.518      0.605      -0.089       0.153
brand_name_Samsung       -0.0313      0.043     -0.725      0.469      -0.116       0.053
brand_name_Sony          -0.0616      0.050     -1.220      0.223      -0.161       0.037
brand_name_Spice         -0.0147      0.063     -0.233      0.816      -0.139       0.109
brand_name_Vivo          -0.0154      0.048     -0.318      0.750      -0.110       0.080
brand_name_XOLO           0.0152      0.055      0.277      0.782      -0.092       0.123
brand_name_Xiaomi         0.0869      0.048      1.806      0.071      -0.007       0.181
brand_name_ZTE           -0.0057      0.047     -0.121      0.904      -0.099       0.087
os_Others                -0.0510      0.033     -1.555      0.120      -0.115       0.013
os_Windows               -0.0207      0.045     -0.459      0.646      -0.109       0.068
os_iOS                   -0.0663      0.146     -0.453      0.651      -0.354       0.221
4g_yes                    0.0528      0.016      3.326      0.001       0.022       0.084
5g_yes                   -0.0714      0.031     -2.268      0.023      -0.133      -0.010
==============================================================================
Omnibus:                      223.612   Durbin-Watson:                   1.910
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              422.275
Skew:                          -0.620   Prob(JB):                     2.01e-92
Kurtosis:                       4.630   Cond. No.                     1.78e+05
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.78e+05. This might indicate that there are
strong multicollinearity or other numerical problems.


# Create user-defined functions to compute measures of model performance.

# Define a function to compute adjusted R-squared.
def adj_r2_score(predictors, targets, predictions):
    r2 = r2_score(targets, predictions)
    n = predictors.shape[0]
    k = predictors.shape[1]
    return 1 - ((1 - r2) * (n - 1) / (n - k - 1))

# Define a function to compute MAPE.
def mape_score(targets, predictions):
    return np.mean(np.abs(targets - predictions) / targets) * 100

# Define a function to compute different metrics to check performance of a regression model.
def model_performance_regression(model, predictors, target):
    """
    Function to compute different metrics to check regression model performance

    model: regressor
    predictors: independent variables
    target: dependent variable
    """

    # Predicting using the independent variables.
    pred = model.predict(predictors)

    r2 = r2_score(target, pred)  # to compute R-squared
    adjr2 = adj_r2_score(predictors, target, pred)  # to compute adjusted R-squared
    rmse = np.sqrt(mean_squared_error(target, pred))  # to compute RMSE
    mae = mean_absolute_error(target, pred)  # to compute MAE
    mape = mape_score(target, pred)  # to compute MAPE

    # Create a dataframe of metrics.
    df_perf = pd.DataFrame(
        {
            "RMSE": rmse,
            "MAE": mae,
            "R-squared": r2,
            "Adj. R-squared": adjr2,
            "MAPE": mape,
        },
        index=[0],
    )

    return df_perf


# Check model performance on the training set.

print("Training Performance\n")
olsmodel_train_perf = model_performance_regression(olsmodel, x_train, y_train)
olsmodel_train_perf

Training Performance


# Check model performance on the test set.

print("Test Performance\n")
olsmodel_test_perf = model_performance_regression(olsmodel, x_test, y_test)
olsmodel_test_perf

Test Performance


# Define a function to check VIF.

def checking_vif(predictors):
    vif = pd.DataFrame()
    vif["feature"] = predictors.columns

    # calculating VIF for each feature
    vif["VIF"] = [
        variance_inflation_factor(predictors.values, i)
        for i in range(len(predictors.columns))
    ]
    return vif


# Display the columns where VIF is > 5.

checking_vif(x_train)[checking_vif(x_train)['VIF']>5]


# Define a function to treat multicollinearity.

def treating_multicollinearity(predictors, target, high_vif_columns):
    """
    Checking the effect of dropping the columns showing high multicollinearity
    on model performance (adj. R-squared and RMSE)

    predictors: independent variables
    target: dependent variable
    high_vif_columns: columns having high VIF
    """
    # empty lists to store adj. R-squared and RMSE values
    adj_r2 = []
    rmse = []

    # build ols models by dropping one of the high VIF columns at a time
    # store the adjusted R-squared and RMSE in the lists defined previously
    for cols in high_vif_columns:
        # defining the new train set
        train = predictors.loc[:, ~predictors.columns.str.startswith(cols)]

        # create the model
        olsmodel = sm.OLS(target, train).fit()

        # adding adj. R-squared and RMSE to the lists
        adj_r2.append(olsmodel.rsquared_adj)
        rmse.append(np.sqrt(olsmodel.mse_resid))

    # creating a dataframe for the results
    temp = pd.DataFrame(
        {
            "col": high_vif_columns,
            "Adj. R-squared after_dropping col": adj_r2,
            "RMSE after dropping col": rmse,
        }
    ).sort_values(by="Adj. R-squared after_dropping col", ascending=False)
    temp.reset_index(drop=True, inplace=True)

    return temp


# Apply the function to the columns with VIF > 5, ignoring the constant and dummy variables.

col_list = ['screen_size', 'weight']

res = treating_multicollinearity(x_train, y_train, col_list)
res


# Drop the screen size column.
col_to_drop = 'screen_size'
x_train2 = x_train.loc[:, ~x_train.columns.str.startswith(col_to_drop)]
x_test2 = x_test.loc[:, ~x_test.columns.str.startswith(col_to_drop)]

# Check VIF after dropping screen size.
vif = checking_vif(x_train2)
print("VIF after dropping ", col_to_drop)
vif[vif['VIF']>5]

VIF after dropping  screen_size


# Print the summary of the new model.

olsmod2 = sm.OLS(y_train, x_train2).fit()
print(olsmod2.summary())

                              OLS Regression Results                             
=================================================================================
Dep. Variable:     normalized_used_price   R-squared:                       0.842
Model:                               OLS   Adj. R-squared:                  0.838
Method:                    Least Squares   F-statistic:                     267.7
Date:                   Fri, 07 Oct 2022   Prob (F-statistic):               0.00
Time:                           00:31:00   Log-Likelihood:                 97.950
No. Observations:                   2417   AIC:                            -99.90
Df Residuals:                       2369   BIC:                             178.0
Df Model:                             47                                         
Covariance Type:               nonrobust                                         
=========================================================================================
                            coef    std err          t      P>|t|      [0.025      0.975]
-----------------------------------------------------------------------------------------
const                     1.5148      0.069     22.089      0.000       1.380       1.649
main_camera_mp            0.0212      0.002     13.979      0.000       0.018       0.024
selfie_camera_mp          0.0138      0.001     12.128      0.000       0.012       0.016
int_memory             9.551e-05   7.04e-05      1.356      0.175   -4.26e-05       0.000
ram                       0.0229      0.005      4.397      0.000       0.013       0.033
battery               -4.284e-06   7.13e-06     -0.601      0.548   -1.83e-05     9.7e-06
weight                    0.0017   9.22e-05     18.376      0.000       0.002       0.002
days_used              2.773e-05   3.11e-05      0.891      0.373   -3.33e-05    8.88e-05
normalized_new_price      0.4413      0.012     35.841      0.000       0.417       0.465
years_since_release      -0.0297      0.005     -6.568      0.000      -0.039      -0.021
brand_name_Alcatel        0.0177      0.048      0.368      0.713      -0.077       0.112
brand_name_Apple          0.0660      0.148      0.445      0.656      -0.225       0.357
brand_name_Asus           0.0013      0.048      0.027      0.978      -0.094       0.096
brand_name_BlackBerry    -0.0444      0.071     -0.626      0.531      -0.183       0.095
brand_name_Celkon        -0.0518      0.067     -0.773      0.440      -0.183       0.080
brand_name_Coolpad        0.0136      0.074      0.185      0.854      -0.131       0.158
brand_name_Gionee         0.0154      0.058      0.265      0.791      -0.099       0.130
brand_name_Google        -0.0587      0.085     -0.687      0.492      -0.226       0.109
brand_name_HTC           -0.0321      0.049     -0.660      0.509      -0.127       0.063
brand_name_Honor          0.0352      0.050      0.708      0.479      -0.062       0.133
brand_name_Huawei        -0.0089      0.045     -0.199      0.842      -0.097       0.079
brand_name_Infinix        0.0450      0.094      0.477      0.634      -0.140       0.230
brand_name_Karbonn        0.0998      0.068      1.472      0.141      -0.033       0.233
brand_name_LG            -0.0325      0.046     -0.712      0.476      -0.122       0.057
brand_name_Lava           0.0276      0.063      0.438      0.661      -0.096       0.151
brand_name_Lenovo         0.0345      0.046      0.756      0.450      -0.055       0.124
brand_name_Meizu         -0.0282      0.057     -0.498      0.618      -0.139       0.083
brand_name_Micromax      -0.0468      0.048     -0.968      0.333      -0.142       0.048
brand_name_Microsoft      0.0773      0.089      0.866      0.387      -0.098       0.252
brand_name_Motorola      -0.0329      0.050     -0.658      0.511      -0.131       0.065
brand_name_Nokia          0.0473      0.052      0.906      0.365      -0.055       0.150
brand_name_OnePlus        0.0684      0.078      0.874      0.382      -0.085       0.222
brand_name_Oppo          -0.0006      0.048     -0.012      0.991      -0.095       0.094
brand_name_Others        -0.0314      0.042     -0.741      0.459      -0.115       0.052
brand_name_Panasonic      0.0482      0.056      0.855      0.393      -0.062       0.159
brand_name_Realme         0.0147      0.062      0.236      0.813      -0.107       0.137
brand_name_Samsung       -0.0458      0.044     -1.049      0.294      -0.131       0.040
brand_name_Sony          -0.0776      0.051     -1.523      0.128      -0.178       0.022
brand_name_Spice         -0.0407      0.064     -0.638      0.524      -0.166       0.084
brand_name_Vivo          -0.0206      0.049     -0.421      0.674      -0.117       0.075
brand_name_XOLO           0.0111      0.055      0.201      0.841      -0.097       0.120
brand_name_Xiaomi         0.0734      0.049      1.511      0.131      -0.022       0.169
brand_name_ZTE           -0.0219      0.048     -0.457      0.647      -0.116       0.072
os_Others                -0.1345      0.031     -4.339      0.000      -0.195      -0.074
os_Windows               -0.0182      0.046     -0.399      0.690      -0.108       0.071
os_iOS                   -0.1657      0.147     -1.125      0.261      -0.455       0.123
4g_yes                    0.0508      0.016      3.167      0.002       0.019       0.082
5g_yes                   -0.0815      0.032     -2.563      0.010      -0.144      -0.019
==============================================================================
Omnibus:                      234.761   Durbin-Watson:                   1.907
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              440.912
Skew:                          -0.647   Prob(JB):                     1.81e-96
Kurtosis:                       4.644   Cond. No.                     1.78e+05
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.78e+05. This might indicate that there are
strong multicollinearity or other numerical problems.


# Define the initial list of columns.
predictors = x_train2.copy()
cols = predictors.columns.tolist()

# Set an initial max p-value.
max_p_value = 1

# Use a while loop to drop columns with the highest p-values one-by-one, recalculating all p-values after each drop until none are above 0.05.

while len(cols) > 0:
    # defining the train set
    x_train_aux = predictors[cols]

    # fitting the model
    model = sm.OLS(y_train, x_train_aux).fit()

    # getting the p-values and the maximum p-value
    p_values = model.pvalues
    max_p_value = max(p_values)

    # name of the variable with maximum p-value
    feature_with_p_max = p_values.idxmax()

    if max_p_value > 0.05:
        cols.remove(feature_with_p_max)
    else:
        break

selected_features = cols
print(selected_features)

['const', 'main_camera_mp', 'selfie_camera_mp', 'ram', 'weight', 'normalized_new_price', 'years_since_release', 'brand_name_Karbonn', 'brand_name_Samsung', 'brand_name_Sony', 'brand_name_Xiaomi', 'os_Others', 'os_iOS', '4g_yes', '5g_yes']


# Create new training and testing sets with high p-value columns dropped.

x_train3 = x_train2[selected_features]
x_test3 = x_test2[selected_features]


# Print the summary of the new model.

olsmod3 = sm.OLS(y_train, x_train3).fit()
print(olsmod3.summary())

                              OLS Regression Results                             
=================================================================================
Dep. Variable:     normalized_used_price   R-squared:                       0.839
Model:                               OLS   Adj. R-squared:                  0.838
Method:                    Least Squares   F-statistic:                     896.9
Date:                   Fri, 07 Oct 2022   Prob (F-statistic):               0.00
Time:                           00:35:33   Log-Likelihood:                 82.004
No. Observations:                   2417   AIC:                            -134.0
Df Residuals:                       2402   BIC:                            -47.15
Df Model:                             14                                         
Covariance Type:               nonrobust                                         
========================================================================================
                           coef    std err          t      P>|t|      [0.025      0.975]
----------------------------------------------------------------------------------------
const                    1.5228      0.049     30.802      0.000       1.426       1.620
main_camera_mp           0.0211      0.001     14.814      0.000       0.018       0.024
selfie_camera_mp         0.0138      0.001     12.838      0.000       0.012       0.016
ram                      0.0211      0.005      4.223      0.000       0.011       0.031
weight                   0.0017      6e-05     27.698      0.000       0.002       0.002
normalized_new_price     0.4419      0.011     39.458      0.000       0.420       0.464
years_since_release     -0.0289      0.003     -8.496      0.000      -0.036      -0.022
brand_name_Karbonn       0.1155      0.055      2.110      0.035       0.008       0.223
brand_name_Samsung      -0.0373      0.016     -2.261      0.024      -0.070      -0.005
brand_name_Sony         -0.0673      0.030     -2.210      0.027      -0.127      -0.008
brand_name_Xiaomi        0.0806      0.026      3.139      0.002       0.030       0.131
os_Others               -0.1258      0.027     -4.603      0.000      -0.179      -0.072
os_iOS                  -0.0897      0.045     -1.988      0.047      -0.178      -0.001
4g_yes                   0.0498      0.015      3.299      0.001       0.020       0.079
5g_yes                  -0.0671      0.031     -2.189      0.029      -0.127      -0.007
==============================================================================
Omnibus:                      245.329   Durbin-Watson:                   1.901
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              481.790
Skew:                          -0.656   Prob(JB):                    2.40e-105
Kurtosis:                       4.749   Cond. No.                     2.39e+03
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 2.39e+03. This might indicate that there are
strong multicollinearity or other numerical problems.


# Check model performance on the training set.

print("Training Performance\n")
olsmod3_train_perf = model_performance_regression(olsmod3, x_train3, y_train)
olsmod3_train_perf

Training Performance


# Check model performance on the test set.

print("Test Performance\n")
olsmod3_test_perf = model_performance_regression(olsmod3, x_test3, y_test)
olsmod3_test_perf

Test Performance


# Create a dataframe with actual, fitted and residual values.
df_pred = pd.DataFrame()

df_pred["Actual Values"] = y_train  # actual values
df_pred["Fitted Values"] = olsmod3.fittedvalues  # predicted values
df_pred["Residuals"] = olsmod3.resid  # residuals

df_pred.head()


# Plot the fitted values vs. residuals.

sns.residplot(
    data=df_pred, x="Fitted Values", y="Residuals", color="purple", lowess=True
)
plt.xlabel("Fitted Values")
plt.ylabel("Residuals")
plt.title("Fitted vs Residual plot");


# Display histogram to check for normality of residuals.

sns.histplot(data=df_pred, x="Residuals", kde=True)
plt.title("Normality of Residuals");


# Display Q-Q plot to visualize normality.

stats.probplot(df_pred["Residuals"], dist="norm", plot=pylab);


# Use Shapiro-Wilk test for normality.

stats.shapiro(df_pred["Residuals"])

ShapiroResult(statistic=0.9678095579147339, pvalue=7.639652123587057e-23)


# Check for homoscedasticity with Goldfeld–Quandt test.

name = ["F statistic", "p-value"]
test = sms.het_goldfeldquandt(df_pred["Residuals"], x_train3)
lzip(name, test)

[('F statistic', 1.009794401185382), ('p-value', 0.43316051505003356)]


# Make copies of the final training and testing sets to test the final model.

x_train_final = x_train3.copy()
x_test_final = x_test3.copy()


# Print the summary of the final model.

olsmodel_final = sm.OLS(y_train, x_train_final).fit()
print(olsmodel_final.summary())

                              OLS Regression Results                             
=================================================================================
Dep. Variable:     normalized_used_price   R-squared:                       0.839
Model:                               OLS   Adj. R-squared:                  0.838
Method:                    Least Squares   F-statistic:                     896.9
Date:                   Fri, 07 Oct 2022   Prob (F-statistic):               0.00
Time:                           00:39:35   Log-Likelihood:                 82.004
No. Observations:                   2417   AIC:                            -134.0
Df Residuals:                       2402   BIC:                            -47.15
Df Model:                             14                                         
Covariance Type:               nonrobust                                         
========================================================================================
                           coef    std err          t      P>|t|      [0.025      0.975]
----------------------------------------------------------------------------------------
const                    1.5228      0.049     30.802      0.000       1.426       1.620
main_camera_mp           0.0211      0.001     14.814      0.000       0.018       0.024
selfie_camera_mp         0.0138      0.001     12.838      0.000       0.012       0.016
ram                      0.0211      0.005      4.223      0.000       0.011       0.031
weight                   0.0017      6e-05     27.698      0.000       0.002       0.002
normalized_new_price     0.4419      0.011     39.458      0.000       0.420       0.464
years_since_release     -0.0289      0.003     -8.496      0.000      -0.036      -0.022
brand_name_Karbonn       0.1155      0.055      2.110      0.035       0.008       0.223
brand_name_Samsung      -0.0373      0.016     -2.261      0.024      -0.070      -0.005
brand_name_Sony         -0.0673      0.030     -2.210      0.027      -0.127      -0.008
brand_name_Xiaomi        0.0806      0.026      3.139      0.002       0.030       0.131
os_Others               -0.1258      0.027     -4.603      0.000      -0.179      -0.072
os_iOS                  -0.0897      0.045     -1.988      0.047      -0.178      -0.001
4g_yes                   0.0498      0.015      3.299      0.001       0.020       0.079
5g_yes                  -0.0671      0.031     -2.189      0.029      -0.127      -0.007
==============================================================================
Omnibus:                      245.329   Durbin-Watson:                   1.901
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              481.790
Skew:                          -0.656   Prob(JB):                    2.40e-105
Kurtosis:                       4.749   Cond. No.                     2.39e+03
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 2.39e+03. This might indicate that there are
strong multicollinearity or other numerical problems.


# Check model performance on the training set.

print("Training Performance\n")
olsmodel_final_train_perf = model_performance_regression(
    olsmodel_final, x_train_final, y_train
)
olsmodel_final_train_perf

Training Performance


# Check model performance on the test set.

print("Test Performance\n")
olsmodel_final_test_perf = model_performance_regression(
    olsmodel_final, x_test_final, y_test
)
olsmodel_final_test_perf

Test Performance


# Import libraries for data manipulation.
import pandas as pd
import numpy as np

# Import libraries for data visualization.
import matplotlib.pyplot as plt
import seaborn as sns

# Import library to split data.
from sklearn.model_selection import train_test_split

# Import predictive model-building libraries.
import statsmodels.stats.api as sms
from statsmodels.stats.outliers_influence import variance_inflation_factor
import statsmodels.api as sm
from statsmodels.tools.tools import add_constant
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree

# Import GridSearch to tune different models.
from sklearn.model_selection import GridSearchCV

# Import functions to evaluate model performance.
from sklearn.metrics import (
    f1_score,
    accuracy_score,
    recall_score,
    precision_score,
    confusion_matrix,
    roc_auc_score,
    plot_confusion_matrix,
    precision_recall_curve,
    roc_curve,
    make_scorer,
)

# Import libraries to ignore irrelevant warnings.
import warnings
warnings.filterwarnings("ignore")
from statsmodels.tools.sm_exceptions import ConvergenceWarning
warnings.simplefilter("ignore", ConvergenceWarning)

# Set the precision of floating numbers to 5 decimal points.
pd.set_option("display.float_format", lambda x: "%.5f" % x)


# Mount Google Drive.

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive


# Load the data set.

data = pd.read_csv('/content/drive/My Drive/Data science/Data sets/INNHotelsGroup.csv')


# Use .shape attribute to display the number of rows & columns in the data set.

data.shape

(36275, 19)


# Display a sample of 5 rows from the data set to get a general idea of the information & make sure it is loaded properly.

data.sample(5)


# Check the number of unique values in the Booking_ID column to see if it should be dropped.

data.Booking_ID.nunique()

36275


# All the Booking ID values are unique, so the column can be dropped as it will not aid in analysis.

data.drop('Booking_ID', axis=1, inplace=True)


# Use .info() method to check the non-null counts and data types of each column.

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 36275 entries, 0 to 36274
Data columns (total 18 columns):
 #   Column                                Non-Null Count  Dtype  
---  ------                                --------------  -----  
 0   no_of_adults                          36275 non-null  int64  
 1   no_of_children                        36275 non-null  int64  
 2   no_of_weekend_nights                  36275 non-null  int64  
 3   no_of_week_nights                     36275 non-null  int64  
 4   type_of_meal_plan                     36275 non-null  object 
 5   required_car_parking_space            36275 non-null  int64  
 6   room_type_reserved                    36275 non-null  object 
 7   lead_time                             36275 non-null  int64  
 8   arrival_year                          36275 non-null  int64  
 9   arrival_month                         36275 non-null  int64  
 10  arrival_date                          36275 non-null  int64  
 11  market_segment_type                   36275 non-null  object 
 12  repeated_guest                        36275 non-null  int64  
 13  no_of_previous_cancellations          36275 non-null  int64  
 14  no_of_previous_bookings_not_canceled  36275 non-null  int64  
 15  avg_price_per_room                    36275 non-null  float64
 16  no_of_special_requests                36275 non-null  int64  
 17  booking_status                        36275 non-null  object 
dtypes: float64(1), int64(13), object(4)
memory usage: 5.0+ MB


# Check the statistical summary for the numeric columns, dropping categorical columns.

data.describe().T.drop(['required_car_parking_space','repeated_guest','arrival_year','arrival_month','arrival_date'])


# Check the statistical summary for the categorical variables.

data.describe(include='object').T


# Check for duplicated values.

data.duplicated().sum()

0


# Use a countplot to visualize which months are busiest.

plt.title('Countplot: Arrival Month')
sns.countplot(data=data, x='arrival_month')
plt.xlabel("Arrival Month")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of market segment types.

plt.title('Countplot: Market Segment Type')
sns.countplot(data=data, x='market_segment_type', order=data['market_segment_type'].value_counts().reset_index()['index'].tolist())
plt.xlabel("Market Segment Type")
plt.ylabel('Count');


# Use a boxplot to visualize variations in distribution of average room price by market segment type.

plt.title('Boxplot: Average Room Price by Market Segment Type')
sns.boxplot(data=data, x='market_segment_type', y='avg_price_per_room', order=data.groupby(['market_segment_type'])['avg_price_per_room'].median().reset_index().sort_values('avg_price_per_room')['market_segment_type'].tolist())
plt.xlabel("Market Segment Type")
plt.ylabel('Average price per room (euros)');


# Use a countplot to visualize the number of bookings canceled vs. not canceled.

plt.title('Countplot: Booking Status')
sns.countplot(data=data, x='booking_status')
plt.xlabel("Booking status")
plt.ylabel('Count');


# Use logical indexing with .shape attribute to calculate the percent of bookings canceled.

data[data['booking_status']=='Canceled'].shape[0]/data.shape[0]*100

32.76361130254997


# Use logical indexing and .shape attribute to calculate percentage of bookings canceled by repeating guests.

repeats = data[data['repeated_guest']==1]
repeats[repeats['booking_status']=='Canceled'].shape[0]/data[data['repeated_guest']==1].shape[0]*100

1.7204301075268817


# Use countplot with hue parameter to visualize differences in cancellation by number of special requests.

plt.title('Countplot: Cancellation by Number of Special Requests')
sns.countplot(data=data, x='no_of_special_requests', hue='booking_status')
plt.legend(loc='upper right')
plt.xlabel("Number of special requests")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of number of adults.

plt.title('Countplot: Number of Adults')
sns.countplot(data=data, x='no_of_adults')
plt.xlabel("Number of Adults")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of number of children.

plt.title('Countplot: Number of Children')
sns.countplot(data=data, x='no_of_children')
plt.xlabel("Number of Children")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of number of weekend nights.

plt.title('Countplot: Number of Weekend Nights')
sns.countplot(data=data, x='no_of_weekend_nights')
plt.xlabel("Number of Weekend Nights")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of number of week nights.

plt.title('Countplot: Number of Week Nights')
sns.countplot(data=data, x='no_of_week_nights')
plt.xlabel("Number of Week Nights")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of meal plans.

plt.title('Countplot: Type of Meal Plan')
sns.countplot(data=data, x='type_of_meal_plan', order=['Not Selected','Meal Plan 1','Meal Plan 2','Meal Plan3'])
plt.xlabel("Type of Meal Plan")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of bookings requiring a car parking space.

plt.title('Countplot: Required Car Parking Space')
sns.countplot(data=data, x='required_car_parking_space')
plt.xlabel("Required Car Parking Space")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of room types reserved.

plt.figure(figsize=(15, 5))
plt.title('Countplot: Room Type Reserved')
sns.countplot(data=data, x='room_type_reserved', order=['Room_Type 1','Room_Type 2','Room_Type 3','Room_Type 4','Room_Type 5','Room_Type 6','Room_Type 7'])
plt.xlabel("Room Type Reserved")
plt.ylabel('Count');


# Create a user-defined function to display histogram & boxplot together for numeric variables.

def histogram_boxplot(data, feature, figsize=(18, 5), kde=True, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (18,5))
    kde: whether to show the density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows=2,  # Number of rows of the subplot grid= 2
        sharex=True,  # x-axis will be shared among all subplots
        gridspec_kw={"height_ratios": (0.3, 0.7)},
        figsize=figsize,
    )  # creating the 2 subplots
    sns.boxplot(
        data=data, x=feature, ax=ax_box2, showmeans=True, color="violet"
    )  # boxplot will be created and a triangle will indicate the mean value of the column
    sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2, bins=bins
    ) if bins else sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2
    )  # For histogram
    ax_hist2.axvline(
        data[feature].mean(), color="green", linestyle="--"
    )  # Add mean to the histogram
    ax_hist2.axvline(
        data[feature].median(), color="black", linestyle="-"
    )  # Add median to the histogram


# Visualize histogram & boxplot for lead time variable.

histogram_boxplot(data=data, feature='lead_time')


# Use a countplot to visualize the distribution of arrival year.

plt.title('Countplot: Arrival Year')
sns.countplot(data=data, x='arrival_year')
plt.xlabel("Arrival Year")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of repeated guests.

plt.title('Countplot: Repeated Guests')
sns.countplot(data=data, x='repeated_guest')
plt.xlabel("Repeated Guests")
plt.ylabel('Count');


# Visualize histogram & boxplot for number of previous cancellations.

histogram_boxplot(data=data, feature='no_of_previous_cancellations')


# Visualize histogram & boxplot for number of previous bookings not canceled.

histogram_boxplot(data=data, feature='no_of_previous_bookings_not_canceled')


# Visualize histogram & boxplot for average price per room.

histogram_boxplot(data=data, feature='avg_price_per_room')


# Use a countplot to visualize the distribution of number of special requests.

plt.title('Countplot: Number of Special Requests')
sns.countplot(data=data, x='no_of_special_requests')
plt.xlabel("Number of Special Requests")
plt.ylabel('Count');


# Use countplot with hue parameter to visualize booking status by month.

plt.title('Countplot: Booking Status by Arrival Month')
sns.countplot(data=data, x='arrival_month', hue='booking_status')
plt.xlabel("Arrival Month")
plt.ylabel('Count');


# Use boxplot to visualize the changes in average room price across different months.

plt.figure(figsize=(15, 5))
plt.title('Boxplot: Average Price per Room by Arrival Month')
sns.boxplot(data=data, x='arrival_month', y='avg_price_per_room')
plt.xlabel("Arrival Month")
plt.ylabel('Average Price per Room (euros)');


# Use a boxplot to visualize the relationship between room price and booking status.

plt.title('Boxplot: Average Price per Room by Booking Status')
sns.boxplot(data=data,x='booking_status',y='avg_price_per_room')
plt.xlabel("Booking Status")
plt.ylabel('Average Price per Room (euros)');


# Use a boxplot to visualize the relationship between lead time and booking status.

plt.title('Boxplot: Lead Time by Booking Status')
sns.boxplot(data=data,x='booking_status',y='lead_time')
plt.xlabel("Booking Status")
plt.ylabel('Lead Time (days)');


# Use countplot with hue parameter to visualize booking status across different market segments.

plt.title('Countplot: Booking Status by Market Segment')
sns.countplot(data=data, x='market_segment_type', hue='booking_status')
plt.xlabel("Market Segment Type")
plt.ylabel('Count');


# Make a new DataFrame to encode booking status to 1 for Canceled bookings and 0 for Not_Canceled.

data1 = data.copy()
data1['booking_status'] = data["booking_status"].apply(lambda x: 1 if x == "Canceled" else 0)


# Use heatmap to visualize correlation between numeric variables.

plt.figure(figsize=(18, 8))
sns.heatmap(data1.corr(), annot=True);


# Check for null values in the data.

data1.isnull().sum()

no_of_adults                            0
no_of_children                          0
no_of_weekend_nights                    0
no_of_week_nights                       0
type_of_meal_plan                       0
required_car_parking_space              0
room_type_reserved                      0
lead_time                               0
arrival_year                            0
arrival_month                           0
arrival_date                            0
market_segment_type                     0
repeated_guest                          0
no_of_previous_cancellations            0
no_of_previous_bookings_not_canceled    0
avg_price_per_room                      0
no_of_special_requests                  0
booking_status                          0
dtype: int64


# Use boxplot to visualize outliers.

numeric_columns = data.select_dtypes(include=np.number).columns.tolist()

plt.figure(figsize=(15, 12))

for i, variable in enumerate(numeric_columns):
    plt.subplot(4, 4, i + 1)
    plt.boxplot(data[variable], whis=1.5)
    plt.tight_layout()
    plt.title(variable)

plt.show()


# Separate the x & y variables and split each into training and testing sets.

X = data1.drop(["booking_status"], axis=1)
Y = data1["booking_status"]

X = sm.add_constant(X)

X = pd.get_dummies(X, drop_first=True)

X_train, X_test, y_train, y_test = train_test_split(
    X, Y, test_size=0.30, random_state=1
)


# Print the features of the training and test sets.

print("Shape of training set : ", X_train.shape)
print("Shape of test set : ", X_test.shape)
print("Percentage of classes in training set:")
print(y_train.value_counts(normalize=True))
print("Percentage of classes in test set:")
print(y_test.value_counts(normalize=True))

Shape of training set :  (25392, 28)
Shape of test set :  (10883, 28)
Percentage of classes in training set:
0   0.67064
1   0.32936
Name: booking_status, dtype: float64
Percentage of classes in test set:
0   0.67638
1   0.32362
Name: booking_status, dtype: float64


# Create a user-defined function to display a DataFrame of model performance metrics.

def model_performance_classification_statsmodels(
    model, predictors, target, threshold=0.5
):
    """
    Function to compute different metrics to check classification model performance

    model: classifier
    predictors: independent variables
    target: dependent variable
    threshold: threshold for classifying the observation as class 1
    """

    # checking which probabilities are greater than threshold
    pred_temp = model.predict(predictors) > threshold
    # rounding off the above values to get classes
    pred = np.round(pred_temp)

    acc = accuracy_score(target, pred)  # to compute accuracy
    recall = recall_score(target, pred)  # to compute recall
    precision = precision_score(target, pred)  # to compute precision
    f1 = f1_score(target, pred)  # to compute F1-score

    # creating a DataFrame of metrics
    df_perf = pd.DataFrame(
        {"Accuracy": acc, "Recall": recall, "Precision": precision, "F1": f1,},
        index=[0],
    )

    return df_perf


# Create a user-defined function to display a confusion matrix for classification models.

def confusion_matrix_statsmodels(model, predictors, target, threshold=0.5):
    """
    To plot the confusion_matrix with percentages

    model: classifier
    predictors: independent variables
    target: dependent variable
    threshold: threshold for classifying the observation as class 1
    """
    y_pred = model.predict(predictors) > threshold
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ["{0:0.0f}".format(item) + "\n{0:.2%}".format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")
    plt.ylabel("True label")
    plt.xlabel("Predicted label")


# Fit the initial logistic regression model.

logit = sm.Logit(y_train, X_train.astype(float))
lg = logit.fit(disp=False)

print(lg.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25364
Method:                           MLE   Df Model:                           27
Date:                Fri, 04 Nov 2022   Pseudo R-squ.:                  0.3293
Time:                        00:54:34   Log-Likelihood:                -10793.
converged:                      False   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                 -924.5923    120.817     -7.653      0.000   -1161.390    -687.795
no_of_adults                             0.1135      0.038      3.017      0.003       0.040       0.187
no_of_children                           0.1563      0.057      2.732      0.006       0.044       0.268
no_of_weekend_nights                     0.1068      0.020      5.398      0.000       0.068       0.146
no_of_week_nights                        0.0398      0.012      3.239      0.001       0.016       0.064
required_car_parking_space              -1.5939      0.138    -11.561      0.000      -1.864      -1.324
lead_time                                0.0157      0.000     58.868      0.000       0.015       0.016
arrival_year                             0.4570      0.060      7.633      0.000       0.340       0.574
arrival_month                           -0.0415      0.006     -6.418      0.000      -0.054      -0.029
arrival_date                             0.0005      0.002      0.252      0.801      -0.003       0.004
repeated_guest                          -2.3469      0.617     -3.805      0.000      -3.556      -1.138
no_of_previous_cancellations             0.2664      0.086      3.108      0.002       0.098       0.434
no_of_previous_bookings_not_canceled    -0.1727      0.153     -1.131      0.258      -0.472       0.127
avg_price_per_room                       0.0188      0.001     25.404      0.000       0.017       0.020
no_of_special_requests                  -1.4690      0.030    -48.790      0.000      -1.528      -1.410
type_of_meal_plan_Meal Plan 2            0.1768      0.067      2.654      0.008       0.046       0.307
type_of_meal_plan_Meal Plan 3           17.8379   5057.795      0.004      0.997   -9895.257    9930.933
type_of_meal_plan_Not Selected           0.2782      0.053      5.245      0.000       0.174       0.382
room_type_reserved_Room_Type 2          -0.3610      0.131     -2.761      0.006      -0.617      -0.105
room_type_reserved_Room_Type 3          -0.0009      1.310     -0.001      0.999      -2.569       2.567
room_type_reserved_Room_Type 4          -0.2821      0.053     -5.305      0.000      -0.386      -0.178
room_type_reserved_Room_Type 5          -0.7176      0.209     -3.432      0.001      -1.127      -0.308
room_type_reserved_Room_Type 6          -0.9456      0.147     -6.434      0.000      -1.234      -0.658
room_type_reserved_Room_Type 7          -1.3964      0.293     -4.767      0.000      -1.971      -0.822
market_segment_type_Complementary      -41.8798   8.42e+05  -4.98e-05      1.000   -1.65e+06    1.65e+06
market_segment_type_Corporate           -1.1935      0.266     -4.487      0.000      -1.715      -0.672
market_segment_type_Offline             -2.1955      0.255     -8.625      0.000      -2.694      -1.697
market_segment_type_Online              -0.3990      0.251     -1.588      0.112      -0.891       0.093
========================================================================================================


# Check the performance of the initial model.

print("Training performance:")
model_performance_classification_statsmodels(lg, X_train, y_train)

Training performance:


# Create a series to sort the independent variables by VIF.

vif_series = pd.Series(
    [variance_inflation_factor(X_train.values, i) for i in range(X_train.shape[1])],
    index=X_train.columns,
    dtype=float,
)

vif_series.sort_values(ascending=False)

const                                  39468156.70600
market_segment_type_Online                   71.17643
market_segment_type_Offline                  64.11392
market_segment_type_Corporate                16.92844
market_segment_type_Complementary             4.50011
avg_price_per_room                            2.05042
no_of_children                                1.97823
room_type_reserved_Room_Type 6                1.97307
repeated_guest                                1.78352
no_of_previous_bookings_not_canceled          1.65199
arrival_year                                  1.43083
no_of_previous_cancellations                  1.39569
lead_time                                     1.39491
room_type_reserved_Room_Type 4                1.36152
no_of_adults                                  1.34815
arrival_month                                 1.27567
type_of_meal_plan_Not Selected                1.27218
type_of_meal_plan_Meal Plan 2                 1.27185
no_of_special_requests                        1.24728
room_type_reserved_Room_Type 7                1.11512
room_type_reserved_Room_Type 2                1.10144
no_of_week_nights                             1.09567
no_of_weekend_nights                          1.06948
required_car_parking_space                    1.03993
room_type_reserved_Room_Type 5                1.02781
type_of_meal_plan_Meal Plan 3                 1.02522
arrival_date                                  1.00674
room_type_reserved_Room_Type 3                1.00330
dtype: float64


# Drop the variable with the highest p-value (market_segment_type_Complementary) and re-check model performance.

X_train1 = X_train.drop(["market_segment_type_Complementary"], axis=1,)
logit1 = sm.Logit(y_train, X_train1.astype(float))
lg1 = logit1.fit(disp=False)
print(lg1.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25365
Method:                           MLE   Df Model:                           26
Date:                Fri, 04 Nov 2022   Pseudo R-squ.:                  0.3284
Time:                        00:55:15   Log-Likelihood:                -10807.
converged:                       True   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                 -924.3903    120.609     -7.664      0.000   -1160.780    -688.000
no_of_adults                             0.1065      0.038      2.839      0.005       0.033       0.180
no_of_children                           0.1522      0.057      2.660      0.008       0.040       0.264
no_of_weekend_nights                     0.1088      0.020      5.506      0.000       0.070       0.147
no_of_week_nights                        0.0420      0.012      3.419      0.001       0.018       0.066
required_car_parking_space              -1.5940      0.138    -11.559      0.000      -1.864      -1.324
lead_time                                0.0157      0.000     58.895      0.000       0.015       0.016
arrival_year                             0.4566      0.060      7.640      0.000       0.339       0.574
arrival_month                           -0.0421      0.006     -6.501      0.000      -0.055      -0.029
arrival_date                             0.0004      0.002      0.203      0.839      -0.003       0.004
repeated_guest                          -2.3217      0.617     -3.761      0.000      -3.531      -1.112
no_of_previous_cancellations             0.2646      0.086      3.088      0.002       0.097       0.433
no_of_previous_bookings_not_canceled    -0.1728      0.152     -1.136      0.256      -0.471       0.125
avg_price_per_room                       0.0191      0.001     26.080      0.000       0.018       0.021
no_of_special_requests                  -1.4700      0.030    -48.847      0.000      -1.529      -1.411
type_of_meal_plan_Meal Plan 2            0.1683      0.067      2.528      0.011       0.038       0.299
type_of_meal_plan_Meal Plan 3            2.2379      1.788      1.252      0.211      -1.266       5.742
type_of_meal_plan_Not Selected           0.2839      0.053      5.355      0.000       0.180       0.388
room_type_reserved_Room_Type 2          -0.3577      0.131     -2.737      0.006      -0.614      -0.102
room_type_reserved_Room_Type 3          -0.0928      1.251     -0.074      0.941      -2.545       2.359
room_type_reserved_Room_Type 4          -0.2805      0.053     -5.276      0.000      -0.385      -0.176
room_type_reserved_Room_Type 5          -0.7338      0.208     -3.521      0.000      -1.142      -0.325
room_type_reserved_Room_Type 6          -0.9616      0.147     -6.546      0.000      -1.250      -0.674
room_type_reserved_Room_Type 7          -1.4362      0.292     -4.916      0.000      -2.009      -0.864
market_segment_type_Corporate           -0.6806      0.250     -2.719      0.007      -1.171      -0.190
market_segment_type_Offline             -1.6774      0.238     -7.053      0.000      -2.144      -1.211
market_segment_type_Online               0.1111      0.235      0.473      0.636      -0.349       0.572
========================================================================================================


# Drop the variable with the highest p-value (room_type_reserved_Room_Type 3) and re-check model performance.

X_train2 = X_train1.drop(["room_type_reserved_Room_Type 3"], axis=1,)
logit2 = sm.Logit(y_train, X_train2.astype(float))
lg2 = logit2.fit(disp=False)
print(lg2.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25366
Method:                           MLE   Df Model:                           25
Date:                Fri, 04 Nov 2022   Pseudo R-squ.:                  0.3284
Time:                        00:55:23   Log-Likelihood:                -10807.
converged:                       True   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                 -924.3678    120.609     -7.664      0.000   -1160.757    -687.979
no_of_adults                             0.1065      0.038      2.839      0.005       0.033       0.180
no_of_children                           0.1522      0.057      2.660      0.008       0.040       0.264
no_of_weekend_nights                     0.1088      0.020      5.506      0.000       0.070       0.148
no_of_week_nights                        0.0420      0.012      3.420      0.001       0.018       0.066
required_car_parking_space              -1.5940      0.138    -11.559      0.000      -1.864      -1.324
lead_time                                0.0157      0.000     58.895      0.000       0.015       0.016
arrival_year                             0.4566      0.060      7.640      0.000       0.339       0.574
arrival_month                           -0.0421      0.006     -6.502      0.000      -0.055      -0.029
arrival_date                             0.0004      0.002      0.203      0.839      -0.003       0.004
repeated_guest                          -2.3216      0.617     -3.761      0.000      -3.531      -1.112
no_of_previous_cancellations             0.2646      0.086      3.088      0.002       0.097       0.433
no_of_previous_bookings_not_canceled    -0.1728      0.152     -1.136      0.256      -0.471       0.125
avg_price_per_room                       0.0191      0.001     26.080      0.000       0.018       0.021
no_of_special_requests                  -1.4700      0.030    -48.849      0.000      -1.529      -1.411
type_of_meal_plan_Meal Plan 2            0.1684      0.067      2.529      0.011       0.038       0.299
type_of_meal_plan_Meal Plan 3            2.2381      1.788      1.252      0.211      -1.266       5.742
type_of_meal_plan_Not Selected           0.2839      0.053      5.356      0.000       0.180       0.388
room_type_reserved_Room_Type 2          -0.3577      0.131     -2.737      0.006      -0.614      -0.102
room_type_reserved_Room_Type 4          -0.2805      0.053     -5.275      0.000      -0.385      -0.176
room_type_reserved_Room_Type 5          -0.7338      0.208     -3.520      0.000      -1.142      -0.325
room_type_reserved_Room_Type 6          -0.9616      0.147     -6.546      0.000      -1.250      -0.674
room_type_reserved_Room_Type 7          -1.4362      0.292     -4.916      0.000      -2.009      -0.864
market_segment_type_Corporate           -0.6803      0.250     -2.718      0.007      -1.171      -0.190
market_segment_type_Offline             -1.6772      0.238     -7.053      0.000      -2.143      -1.211
market_segment_type_Online               0.1114      0.235      0.474      0.635      -0.349       0.572
========================================================================================================


# Drop the variable with the highest p-value (arrival_date) and re-check model performance.

X_train3 = X_train2.drop(["arrival_date"], axis=1,)
logit3 = sm.Logit(y_train, X_train3.astype(float))
lg3 = logit3.fit(disp=False)
print(lg3.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25367
Method:                           MLE   Df Model:                           24
Date:                Fri, 04 Nov 2022   Pseudo R-squ.:                  0.3284
Time:                        00:55:31   Log-Likelihood:                -10807.
converged:                       True   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                 -924.3411    120.612     -7.664      0.000   -1160.737    -687.945
no_of_adults                             0.1067      0.038      2.845      0.004       0.033       0.180
no_of_children                           0.1523      0.057      2.663      0.008       0.040       0.264
no_of_weekend_nights                     0.1089      0.020      5.514      0.000       0.070       0.148
no_of_week_nights                        0.0419      0.012      3.418      0.001       0.018       0.066
required_car_parking_space              -1.5941      0.138    -11.560      0.000      -1.864      -1.324
lead_time                                0.0157      0.000     58.907      0.000       0.015       0.016
arrival_year                             0.4566      0.060      7.639      0.000       0.339       0.574
arrival_month                           -0.0421      0.006     -6.524      0.000      -0.055      -0.029
repeated_guest                          -2.3226      0.617     -3.762      0.000      -3.533      -1.112
no_of_previous_cancellations             0.2645      0.086      3.086      0.002       0.097       0.433
no_of_previous_bookings_not_canceled    -0.1727      0.152     -1.136      0.256      -0.471       0.125
avg_price_per_room                       0.0191      0.001     26.081      0.000       0.018       0.021
no_of_special_requests                  -1.4698      0.030    -48.858      0.000      -1.529      -1.411
type_of_meal_plan_Meal Plan 2            0.1687      0.067      2.534      0.011       0.038       0.299
type_of_meal_plan_Meal Plan 3            2.2395      1.787      1.253      0.210      -1.262       5.741
type_of_meal_plan_Not Selected           0.2840      0.053      5.358      0.000       0.180       0.388
room_type_reserved_Room_Type 2          -0.3573      0.131     -2.734      0.006      -0.613      -0.101
room_type_reserved_Room_Type 4          -0.2803      0.053     -5.273      0.000      -0.385      -0.176
room_type_reserved_Room_Type 5          -0.7336      0.208     -3.520      0.000      -1.142      -0.325
room_type_reserved_Room_Type 6          -0.9615      0.147     -6.546      0.000      -1.249      -0.674
room_type_reserved_Room_Type 7          -1.4359      0.292     -4.915      0.000      -2.008      -0.863
market_segment_type_Corporate           -0.6798      0.250     -2.716      0.007      -1.170      -0.189
market_segment_type_Offline             -1.6777      0.238     -7.055      0.000      -2.144      -1.212
market_segment_type_Online               0.1111      0.235      0.473      0.636      -0.349       0.571
========================================================================================================


# Drop the variable with the highest p-value (market_segment_type_Online) and re-check model performance.

X_train4 = X_train3.drop(["market_segment_type_Online"], axis=1,)
logit4 = sm.Logit(y_train, X_train4.astype(float))
lg4 = logit4.fit(disp=False)
print(lg4.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25368
Method:                           MLE   Df Model:                           23
Date:                Fri, 04 Nov 2022   Pseudo R-squ.:                  0.3284
Time:                        00:55:53   Log-Likelihood:                -10807.
converged:                       True   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                 -921.5770    120.475     -7.650      0.000   -1157.704    -685.450
no_of_adults                             0.1086      0.037      2.914      0.004       0.036       0.182
no_of_children                           0.1527      0.057      2.670      0.008       0.041       0.265
no_of_weekend_nights                     0.1088      0.020      5.511      0.000       0.070       0.148
no_of_week_nights                        0.0418      0.012      3.409      0.001       0.018       0.066
required_car_parking_space              -1.5952      0.138    -11.570      0.000      -1.865      -1.325
lead_time                                0.0157      0.000     59.180      0.000       0.015       0.016
arrival_year                             0.4553      0.060      7.625      0.000       0.338       0.572
arrival_month                           -0.0423      0.006     -6.562      0.000      -0.055      -0.030
repeated_guest                          -2.3315      0.617     -3.781      0.000      -3.540      -1.123
no_of_previous_cancellations             0.2654      0.086      3.097      0.002       0.097       0.433
no_of_previous_bookings_not_canceled    -0.1726      0.152     -1.135      0.257      -0.471       0.126
avg_price_per_room                       0.0191      0.001     26.344      0.000       0.018       0.021
no_of_special_requests                  -1.4694      0.030    -48.871      0.000      -1.528      -1.410
type_of_meal_plan_Meal Plan 2            0.1674      0.067      2.516      0.012       0.037       0.298
type_of_meal_plan_Meal Plan 3            2.1843      1.753      1.246      0.213      -1.251       5.620
type_of_meal_plan_Not Selected           0.2858      0.053      5.405      0.000       0.182       0.389
room_type_reserved_Room_Type 2          -0.3561      0.131     -2.726      0.006      -0.612      -0.100
room_type_reserved_Room_Type 4          -0.2822      0.053     -5.322      0.000      -0.386      -0.178
room_type_reserved_Room_Type 5          -0.7348      0.208     -3.527      0.000      -1.143      -0.326
room_type_reserved_Room_Type 6          -0.9644      0.147     -6.571      0.000      -1.252      -0.677
room_type_reserved_Room_Type 7          -1.4409      0.292     -4.936      0.000      -2.013      -0.869
market_segment_type_Corporate           -0.7877      0.103     -7.664      0.000      -0.989      -0.586
market_segment_type_Offline             -1.7874      0.052    -34.398      0.000      -1.889      -1.686
========================================================================================================


# Drop the variable with the highest p-value (no_of_previous_bookings_not_canceled) and re-check model performance.

X_train5 = X_train4.drop(["no_of_previous_bookings_not_canceled"], axis=1,)
logit5 = sm.Logit(y_train, X_train5.astype(float))
lg5 = logit5.fit(disp=False)
print(lg5.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25369
Method:                           MLE   Df Model:                           22
Date:                Fri, 04 Nov 2022   Pseudo R-squ.:                  0.3283
Time:                        00:56:01   Log-Likelihood:                -10808.
converged:                       True   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
==================================================================================================
                                     coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------
const                           -919.9661    120.487     -7.635      0.000   -1156.117    -683.816
no_of_adults                       0.1086      0.037      2.913      0.004       0.036       0.182
no_of_children                     0.1527      0.057      2.670      0.008       0.041       0.265
no_of_weekend_nights               0.1088      0.020      5.508      0.000       0.070       0.147
no_of_week_nights                  0.0418      0.012      3.406      0.001       0.018       0.066
required_car_parking_space        -1.5946      0.138    -11.564      0.000      -1.865      -1.324
lead_time                          0.0157      0.000     59.223      0.000       0.015       0.016
arrival_year                       0.4545      0.060      7.611      0.000       0.337       0.571
arrival_month                     -0.0423      0.006     -6.561      0.000      -0.055      -0.030
repeated_guest                    -2.7372      0.557     -4.916      0.000      -3.828      -1.646
no_of_previous_cancellations       0.2289      0.077      2.984      0.003       0.079       0.379
avg_price_per_room                 0.0192      0.001     26.354      0.000       0.018       0.021
no_of_special_requests            -1.4699      0.030    -48.890      0.000      -1.529      -1.411
type_of_meal_plan_Meal Plan 2      0.1664      0.067      2.502      0.012       0.036       0.297
type_of_meal_plan_Meal Plan 3      2.1848      1.754      1.245      0.213      -1.254       5.623
type_of_meal_plan_Not Selected     0.2858      0.053      5.405      0.000       0.182       0.389
room_type_reserved_Room_Type 2    -0.3564      0.131     -2.728      0.006      -0.613      -0.100
room_type_reserved_Room_Type 4    -0.2824      0.053     -5.326      0.000      -0.386      -0.178
room_type_reserved_Room_Type 5    -0.7349      0.208     -3.528      0.000      -1.143      -0.327
room_type_reserved_Room_Type 6    -0.9649      0.147     -6.574      0.000      -1.253      -0.677
room_type_reserved_Room_Type 7    -1.4416      0.292     -4.938      0.000      -2.014      -0.869
market_segment_type_Corporate     -0.7925      0.103     -7.709      0.000      -0.994      -0.591
market_segment_type_Offline       -1.7875      0.052    -34.400      0.000      -1.889      -1.686
==================================================================================================


# Drop the variable with the highest p-value (type_of_meal_plan_Meal Plan 3) and re-check model performance.

X_train6 = X_train5.drop(["type_of_meal_plan_Meal Plan 3"], axis=1,)
logit6 = sm.Logit(y_train, X_train6.astype(float))
lg6 = logit6.fit(disp=False)
print(lg6.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25370
Method:                           MLE   Df Model:                           21
Date:                Fri, 04 Nov 2022   Pseudo R-squ.:                  0.3283
Time:                        00:56:07   Log-Likelihood:                -10809.
converged:                       True   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
==================================================================================================
                                     coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------
const                           -917.2860    120.456     -7.615      0.000   -1153.376    -681.196
no_of_adults                       0.1086      0.037      2.914      0.004       0.036       0.182
no_of_children                     0.1522      0.057      2.660      0.008       0.040       0.264
no_of_weekend_nights               0.1086      0.020      5.501      0.000       0.070       0.147
no_of_week_nights                  0.0418      0.012      3.403      0.001       0.018       0.066
required_car_parking_space        -1.5943      0.138    -11.561      0.000      -1.865      -1.324
lead_time                          0.0157      0.000     59.218      0.000       0.015       0.016
arrival_year                       0.4531      0.060      7.591      0.000       0.336       0.570
arrival_month                     -0.0424      0.006     -6.568      0.000      -0.055      -0.030
repeated_guest                    -2.7365      0.557     -4.915      0.000      -3.828      -1.645
no_of_previous_cancellations       0.2289      0.077      2.983      0.003       0.078       0.379
avg_price_per_room                 0.0192      0.001     26.343      0.000       0.018       0.021
no_of_special_requests            -1.4699      0.030    -48.892      0.000      -1.529      -1.411
type_of_meal_plan_Meal Plan 2      0.1654      0.067      2.487      0.013       0.035       0.296
type_of_meal_plan_Not Selected     0.2858      0.053      5.405      0.000       0.182       0.389
room_type_reserved_Room_Type 2    -0.3560      0.131     -2.725      0.006      -0.612      -0.100
room_type_reserved_Room_Type 4    -0.2826      0.053     -5.330      0.000      -0.387      -0.179
room_type_reserved_Room_Type 5    -0.7352      0.208     -3.529      0.000      -1.143      -0.327
room_type_reserved_Room_Type 6    -0.9650      0.147     -6.572      0.000      -1.253      -0.677
room_type_reserved_Room_Type 7    -1.4312      0.293     -4.892      0.000      -2.005      -0.858
market_segment_type_Corporate     -0.7928      0.103     -7.711      0.000      -0.994      -0.591
market_segment_type_Offline       -1.7867      0.052    -34.391      0.000      -1.889      -1.685
==================================================================================================


# Check the performance of the model after dropping insignificant variables.

print("Training performance:")
model_performance_classification_statsmodels(lg6, X_train6, y_train)

Training performance:


# Convert coefficients to odds.
odds = np.exp(lg6.params)

# Find the percent change.
perc_change_odds = (odds - 1) * 100

# Create a DataFrame with odds.
pd.DataFrame({"Odds": odds, "% change": perc_change_odds}, index=X_train6.columns).sort_values('% change',ascending=False)


# Create a confusion matrix to check model performance on the training set.

confusion_matrix_statsmodels(lg6, X_train6, y_train)


# Display the model performance metrics DataFrame.

log_reg_model_train_perf = model_performance_classification_statsmodels(lg6, X_train6, y_train)

print("Training performance:")
log_reg_model_train_perf

Training performance:


# Plot the ROC-AUC on the training data.

logit_roc_auc_train = roc_auc_score(y_train, lg6.predict(X_train6))
fpr, tpr, thresholds = roc_curve(y_train, lg6.predict(X_train6))
plt.figure(figsize=(7, 5))
plt.plot(fpr, tpr, label="Logistic Regression (area = %0.2f)" % logit_roc_auc_train)
plt.plot([0, 1], [0, 1], "r--")
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel("False Positive Rate")
plt.ylabel("True Positive Rate")
plt.title("Receiver operating characteristic")
plt.legend(loc="lower right")
plt.show()


# Find the optimal threshold from the AUC-ROC curve, where TPR is high and FPR is low.

fpr, tpr, thresholds = roc_curve(y_train, lg6.predict(X_train6))

optimal_idx = np.argmax(tpr - fpr)
optimal_threshold_auc_roc = thresholds[optimal_idx]
print(optimal_threshold_auc_roc)

0.37104666234889655


# Display the confusion matrix using the optimal threshold.

confusion_matrix_statsmodels(lg6, X_train6, y_train, threshold=optimal_threshold_auc_roc)


# Check model performance using the optimal threshold.

log_reg_model_train_perf_threshold_auc_roc = model_performance_classification_statsmodels(
    lg6, X_train6, y_train, threshold=optimal_threshold_auc_roc
)
print("Training performance:")
log_reg_model_train_perf_threshold_auc_roc

Training performance:


# Plot a precision-recall curve to check for a better threshold.

y_scores = lg6.predict(X_train6)
prec, rec, tre = precision_recall_curve(y_train, y_scores,)

def plot_prec_recall_vs_tresh(precisions, recalls, thresholds):
    plt.plot(thresholds, precisions[:-1], "b--", label="precision")
    plt.plot(thresholds, recalls[:-1], "g--", label="recall")
    plt.xlabel("Threshold")
    plt.legend(loc="upper left")
    plt.ylim([0, 1])

plt.figure(figsize=(10, 7))
plot_prec_recall_vs_tresh(prec, rec, tre)
plt.show()


# Set the new threshold where precision and recall meet.

optimal_threshold_curve = 0.42


# Check the confusion matrix with the new threshold.

confusion_matrix_statsmodels(lg6, X_train6, y_train, threshold=optimal_threshold_curve)


# Check the performance measures DataFrame with the new threshold.

log_reg_model_train_perf_threshold_curve = model_performance_classification_statsmodels(
    lg6, X_train6, y_train, threshold=optimal_threshold_curve
)
print("Training performance:")
log_reg_model_train_perf_threshold_curve

Training performance:


# Drop the columns that were dropped from the training set.

X_test6 = X_test[X_train6.columns].astype(float)


# Diplay confusion matrix for the default threshold on the test data.

confusion_matrix_statsmodels(lg6, X_test6, y_test)


# Display performance measures DataFrame.

log_reg_model_test_perf = model_performance_classification_statsmodels(lg6, X_test6, y_test)

print("Test performance:")
log_reg_model_test_perf

Test performance:


# Plot ROC curve.

logit_roc_auc_train = roc_auc_score(y_test, lg6.predict(X_test6))
fpr, tpr, thresholds = roc_curve(y_test, lg6.predict(X_test6))
plt.figure(figsize=(7, 5))
plt.plot(fpr, tpr, label="Logistic Regression (area = %0.2f)" % logit_roc_auc_train)
plt.plot([0, 1], [0, 1], "r--")
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel("False Positive Rate")
plt.ylabel("True Positive Rate")
plt.title("Receiver operating characteristic")
plt.legend(loc="lower right")
plt.show()


# Diplay confusion matrix.

confusion_matrix_statsmodels(lg6, X_test6, y_test, threshold=optimal_threshold_auc_roc)


# Display performance measures DataFrame.

log_reg_model_test_perf_threshold_auc_roc = model_performance_classification_statsmodels(
    lg6, X_test6, y_test, threshold=optimal_threshold_auc_roc
)
print("Test performance:")
log_reg_model_test_perf_threshold_auc_roc

Test performance:


# Diplay confusion matrix.

confusion_matrix_statsmodels(lg6, X_test6, y_test, threshold=optimal_threshold_curve)


# Display performance measures DataFrame.

log_reg_model_test_perf_threshold_curve = model_performance_classification_statsmodels(
    lg6, X_test6, y_test, threshold=optimal_threshold_curve
)
print("Test performance:")
log_reg_model_test_perf_threshold_curve

Test performance:


# Create a DataFrame to summarize the performance measures of each model on the training data.

models_train_comp_df = pd.concat(
    [
        log_reg_model_train_perf.T,
        log_reg_model_train_perf_threshold_auc_roc.T,
        log_reg_model_train_perf_threshold_curve.T,
    ],
    axis=1,
)
models_train_comp_df.columns = [
    "Logistic Regression statsmodel",
    "Logistic Regression-0.37 Threshold",
    "Logistic Regression-0.42 Threshold",
]

print("Training performance comparison:")
models_train_comp_df

Training performance comparison:


# Create a DataFrame to summarize the performance measures of each model on the test data.

models_test_comp_df = pd.concat(
    [
        log_reg_model_test_perf.T,
        log_reg_model_test_perf_threshold_auc_roc.T,
        log_reg_model_test_perf_threshold_curve.T,
    ],
    axis=1,
)
models_test_comp_df.columns = [
    "Logistic Regression statsmodel",
    "Logistic Regression-0.37 Threshold",
    "Logistic Regression-0.42 Threshold",
]

print("Test set performance comparison:")
models_test_comp_df

Test set performance comparison:


# Prepare the data for decision tree modeling & split into training & test sets.

X = data1.drop(["booking_status"], axis=1)
Y = data1["booking_status"]

X = pd.get_dummies(X, drop_first=True)

X_train, X_test, y_train, y_test = train_test_split(
    X, Y, test_size=0.30, random_state=1
)


# Build the decision tree model.

model0 = DecisionTreeClassifier(random_state=1)
model0.fit(X_train, y_train)

DecisionTreeClassifier(random_state=1)


# Create a user-defined function to compute & display performance metrics.

def model_performance_classification_sklearn(model, predictors, target):
    """
    Function to compute different metrics to check classification model performance

    model: classifier
    predictors: independent variables
    target: dependent variable
    """

    # predicting using the independent variables
    pred = model.predict(predictors)

    acc = accuracy_score(target, pred)  # to compute accuracy
    recall = recall_score(target, pred)  # to compute recall
    precision = precision_score(target, pred)  # to compute precision
    f1 = f1_score(target, pred)  # to compute F1-score

    # creating a DataFrame of metrics
    df_perf = pd.DataFrame(
        {"Accuracy": acc, "Recall": recall, "Precision": precision, "F1": f1,},
        index=[0],
    )

    return df_perf


# Create a user-defined function to display a confusion matrix for the decision tree model.

def confusion_matrix_sklearn(model, predictors, target):
    """
    To plot the confusion_matrix with percentages

    model: classifier
    predictors: independent variables
    target: dependent variable
    """
    y_pred = model.predict(predictors)
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ["{0:0.0f}".format(item) + "\n{0:.2%}".format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")
    plt.ylabel("True label")
    plt.xlabel("Predicted label")


# Display the confusion matrix for the default model on the training data.

confusion_matrix_sklearn(model0, X_train, y_train)


# Compute the performance measures on the training data.

decision_tree_perf_train = model_performance_classification_sklearn(
    model0, X_train, y_train
)
decision_tree_perf_train


# Display the confusion matrix on the testing data.

confusion_matrix_sklearn(model0, X_test, y_test)


decision_tree_perf_test = model_performance_classification_sklearn(
    model0, X_test, y_test
)
decision_tree_perf_test


# Check feature importance for the non-pruned model.

feature_names = list(X_train.columns)
importances = model0.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(8, 8))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()


# Choose the type of classifier
estimator = DecisionTreeClassifier(random_state=1, class_weight="balanced")

# Grid of parameters to choose from
parameters = {
    "max_depth": np.arange(2, 7, 2),
    "max_leaf_nodes": [50, 75, 150, 250],
    "min_samples_split": [10, 30, 50, 70],
}

# Type of scoring used to compare parameter combinations
acc_scorer = make_scorer(f1_score)

# Run the grid search
grid_obj = GridSearchCV(estimator, parameters, scoring=acc_scorer, cv=5)
grid_obj = grid_obj.fit(X_train, y_train)

# Set the clf to the best combination of parameters
estimator = grid_obj.best_estimator_

# Fit the best algorithm to the data.
estimator.fit(X_train, y_train)

DecisionTreeClassifier(class_weight='balanced', max_depth=6, max_leaf_nodes=50,
                       min_samples_split=10, random_state=1)


# Check the confusion matrix for the pre-pruned tree on the training data.

confusion_matrix_sklearn(estimator, X_train, y_train)


# Check the performance measures for the pre-pruned tree on the training data.

decision_tree_tune_perf_train = model_performance_classification_sklearn(
    estimator, X_train, y_train
)
decision_tree_tune_perf_train


# Check the confusion matrix for the pre-pruned model on the test data.

confusion_matrix_sklearn(estimator, X_test, y_test)


# Check the performance measures for the pre-pruned tree on the test data.

decision_tree_tune_perf_test = model_performance_classification_sklearn(
    estimator, X_test, y_test
)
decision_tree_tune_perf_test


# Visualize the decision tree.

plt.figure(figsize=(20, 10))
out = tree.plot_tree(
    estimator,
    feature_names=feature_names,
    filled=True,
    fontsize=9,
    node_ids=False,
    class_names=None,
)

# Add arrows to the decision tree split if they are missing.
for o in out:
    arrow = o.arrow_patch
    if arrow is not None:
        arrow.set_edgecolor("black")
        arrow.set_linewidth(1)
plt.show()


# Display the text report for the pre-pruned decision tree.

print(tree.export_text(estimator, feature_names=feature_names, show_weights=True))

|--- lead_time <= 151.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 196.50
|   |   |   |   |   |   |--- weights: [1736.39, 132.08] class: 0
|   |   |   |   |   |--- avg_price_per_room >  196.50
|   |   |   |   |   |   |--- weights: [0.75, 25.81] class: 1
|   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |--- weights: [960.27, 223.16] class: 0
|   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |--- weights: [129.73, 160.92] class: 1
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- lead_time <= 117.50
|   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |--- weights: [214.72, 227.72] class: 1
|   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |--- weights: [82.76, 285.41] class: 1
|   |   |   |   |--- lead_time >  117.50
|   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |--- weights: [87.23, 81.98] class: 0
|   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |--- weights: [228.14, 48.58] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- lead_time <= 13.50
|   |   |   |   |--- avg_price_per_room <= 99.44
|   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |--- weights: [92.45, 0.00] class: 0
|   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |--- weights: [363.83, 132.08] class: 0
|   |   |   |   |--- avg_price_per_room >  99.44
|   |   |   |   |   |--- lead_time <= 3.50
|   |   |   |   |   |   |--- weights: [219.94, 85.01] class: 0
|   |   |   |   |   |--- lead_time >  3.50
|   |   |   |   |   |   |--- weights: [132.71, 280.85] class: 1
|   |   |   |--- lead_time >  13.50
|   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 71.92
|   |   |   |   |   |   |--- weights: [158.80, 159.40] class: 1
|   |   |   |   |   |--- avg_price_per_room >  71.92
|   |   |   |   |   |   |--- weights: [850.67, 3543.28] class: 1
|   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |--- weights: [48.46, 1.52] class: 0
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |--- lead_time <= 102.50
|   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |--- weights: [697.09, 9.11] class: 0
|   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |--- weights: [15.66, 9.11] class: 0
|   |   |   |   |--- lead_time >  102.50
|   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |--- weights: [32.06, 19.74] class: 0
|   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |--- weights: [44.73, 3.04] class: 0
|   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |--- lead_time <= 8.50
|   |   |   |   |   |--- lead_time <= 4.50
|   |   |   |   |   |   |--- weights: [498.03, 44.03] class: 0
|   |   |   |   |   |--- lead_time >  4.50
|   |   |   |   |   |   |--- weights: [258.71, 63.76] class: 0
|   |   |   |   |--- lead_time >  8.50
|   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |--- weights: [2512.51, 1451.32] class: 0
|   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |--- weights: [134.20, 1.52] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |--- weights: [1585.04, 0.00] class: 0
|   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- weights: [180.42, 57.69] class: 0
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [52.19, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |--- weights: [184.90, 56.17] class: 0
|   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |--- weights: [106.61, 106.27] class: 0
|   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |--- weights: [67.10, 0.00] class: 0
|--- lead_time >  151.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- no_of_special_requests <= 0.50
|   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |--- lead_time <= 163.50
|   |   |   |   |   |   |--- weights: [3.73, 24.29] class: 1
|   |   |   |   |   |--- lead_time >  163.50
|   |   |   |   |   |   |--- weights: [257.96, 62.24] class: 0
|   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |--- avg_price_per_room <= 2.50
|   |   |   |   |   |   |--- weights: [8.95, 3.04] class: 0
|   |   |   |   |   |--- avg_price_per_room >  2.50
|   |   |   |   |   |   |--- weights: [0.75, 97.16] class: 1
|   |   |   |--- no_of_adults >  1.50
|   |   |   |   |--- avg_price_per_room <= 82.47
|   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |--- weights: [2.98, 282.37] class: 1
|   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |--- weights: [213.97, 385.60] class: 1
|   |   |   |   |--- avg_price_per_room >  82.47
|   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |--- weights: [23.86, 1030.80] class: 1
|   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |--- no_of_special_requests >  0.50
|   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |--- lead_time <= 180.50
|   |   |   |   |   |--- lead_time <= 159.50
|   |   |   |   |   |   |--- weights: [7.46, 7.59] class: 1
|   |   |   |   |   |--- lead_time >  159.50
|   |   |   |   |   |   |--- weights: [37.28, 4.55] class: 0
|   |   |   |   |--- lead_time >  180.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- weights: [20.13, 212.54] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |--- weights: [231.12, 110.82] class: 0
|   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |--- weights: [19.38, 34.92] class: 1
|   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |--- lead_time <= 348.50
|   |   |   |   |   |   |--- weights: [106.61, 3.04] class: 0
|   |   |   |   |   |--- lead_time >  348.50
|   |   |   |   |   |   |--- weights: [5.96, 4.55] class: 0
|   |--- avg_price_per_room >  100.04
|   |   |--- arrival_month <= 11.50
|   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |--- weights: [0.00, 3200.19] class: 1
|   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |--- arrival_month >  11.50
|   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |--- weights: [35.04, 0.00] class: 0
|   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |--- weights: [3.73, 22.77] class: 1


# Check the feature importances for the pre-pruned model.

importances = estimator.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(8, 8))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()


# Create a DataFrame to display alpha levels and corresponding impurities.

clf = DecisionTreeClassifier(random_state=1, class_weight="balanced")
path = clf.cost_complexity_pruning_path(X_train, y_train)
ccp_alphas, impurities = abs(path.ccp_alphas), path.impurities
pd.DataFrame(path)


# Plot impurity vs. alpha for the training set.

fig, ax = plt.subplots(figsize=(10, 5))
ax.plot(ccp_alphas[:-1], impurities[:-1], marker="o", drawstyle="steps-post")
ax.set_xlabel("effective alpha")
ax.set_ylabel("total impurity of leaves")
ax.set_title("Total Impurity vs effective alpha for training set")
plt.show()


# Train a decision tree using the effective alphas.

clfs = []
for ccp_alpha in ccp_alphas:
    clf = DecisionTreeClassifier(
        random_state=1, ccp_alpha=ccp_alpha, class_weight="balanced"
    )
    clf.fit(X_train, y_train)
    clfs.append(clf)
print(
    "Number of nodes in the last tree is: {} with ccp_alpha: {}".format(
        clfs[-1].tree_.node_count, ccp_alphas[-1]
    )
)

Number of nodes in the last tree is: 1 with ccp_alpha: 0.08117914389136943


# Remove the last element with only one node and plot # of nodes vs. alpha as well as depth vs. alpha.

clfs = clfs[:-1]
ccp_alphas = ccp_alphas[:-1]

node_counts = [clf.tree_.node_count for clf in clfs]
depth = [clf.tree_.max_depth for clf in clfs]
fig, ax = plt.subplots(2, 1, figsize=(10, 7))
ax[0].plot(ccp_alphas, node_counts, marker="o", drawstyle="steps-post")
ax[0].set_xlabel("alpha")
ax[0].set_ylabel("number of nodes")
ax[0].set_title("Number of nodes vs alpha")
ax[1].plot(ccp_alphas, depth, marker="o", drawstyle="steps-post")
ax[1].set_xlabel("alpha")
ax[1].set_ylabel("depth of tree")
ax[1].set_title("Depth vs alpha")
fig.tight_layout()


# Compute the F1 score on the training and test data for each of the post-pruned models.

f1_train = []
for clf in clfs:
    pred_train = clf.predict(X_train)
    values_train = f1_score(y_train, pred_train)
    f1_train.append(values_train)

f1_test = []
for clf in clfs:
    pred_test = clf.predict(X_test)
    values_test = f1_score(y_test, pred_test)
    f1_test.append(values_test)


# Plot the F1 score vs. alpha on the training and test data.

fig, ax = plt.subplots(figsize=(15, 5))
ax.set_xlabel("alpha")
ax.set_ylabel("F1 Score")
ax.set_title("F1 Score vs alpha for training and testing sets")
ax.plot(ccp_alphas, f1_train, marker="o", label="train", drawstyle="steps-post")
ax.plot(ccp_alphas, f1_test, marker="o", label="test", drawstyle="steps-post")
ax.legend()
plt.show()


# Return the alpha level that optimizes F1 score on the training and testing data.

index_best_model = np.argmax(f1_test)
best_model = clfs[index_best_model]
print(best_model)

DecisionTreeClassifier(ccp_alpha=0.0001226763315516701, class_weight='balanced',
                       random_state=1)


# Display the confusion matrix for the best post-pruned model on the training data.

confusion_matrix_sklearn(best_model, X_train, y_train)


# Display the model performance measures for the best post-pruned model on the training data.

decision_tree_post_perf_train = model_performance_classification_sklearn(
    best_model, X_train, y_train
)
decision_tree_post_perf_train


# Display the confusion matrix for the best post-pruned model on the test data.

confusion_matrix_sklearn(best_model, X_test, y_test)


# Display the model performance measures for the best post-pruned model on the test data.

decision_tree_post_test = model_performance_classification_sklearn(
    best_model, X_test, y_test
)
decision_tree_post_test


# Display the post-pruned decision tree.

plt.figure(figsize=(20, 10))

out = tree.plot_tree(
    best_model,
    feature_names=feature_names,
    filled=True,
    fontsize=9,
    node_ids=False,
    class_names=None,
)
for o in out:
    arrow = o.arrow_patch
    if arrow is not None:
        arrow.set_edgecolor("black")
        arrow.set_linewidth(1)
plt.show()


# Print the text report for the post-pruned decision tree.

print(tree.export_text(best_model, feature_names=feature_names, show_weights=True))

|--- lead_time <= 151.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 196.50
|   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |--- lead_time <= 16.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 68.50
|   |   |   |   |   |   |   |   |   |--- weights: [207.26, 10.63] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  68.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 29.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |--- arrival_date >  29.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 7.59] class: 1
|   |   |   |   |   |   |   |--- lead_time >  16.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 135.00
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- repeated_guest <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- repeated_guest >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [21.62, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  135.00
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 12.14] class: 1
|   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |--- weights: [1199.59, 0.00] class: 0
|   |   |   |   |   |--- avg_price_per_room >  196.50
|   |   |   |   |   |   |--- weights: [0.75, 25.81] class: 1
|   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 63.29
|   |   |   |   |   |   |   |   |--- arrival_date <= 20.50
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [41.75, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  20.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 59.75
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 23.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.49, 12.14] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  23.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [14.91, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  59.75
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 44.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 59.21] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  44.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  63.29
|   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 3.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 59.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- lead_time >  59.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [20.13, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  3.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.75, 15.18] class: 1
|   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |--- weights: [413.04, 27.33] class: 0
|   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |--- avg_price_per_room <= 99.98
|   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 62.50
|   |   |   |   |   |   |   |   |   |--- weights: [15.66, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  62.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 80.38
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 81.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  81.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  80.38
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |   |--- weights: [55.17, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 73.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  73.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [21.62, 4.55] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  99.98
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 132.43
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 122.97] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  132.43
|   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- lead_time <= 117.50
|   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |--- avg_price_per_room <= 75.07
|   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 58.75
|   |   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  58.75
|   |   |   |   |   |   |   |   |   |--- no_of_previous_bookings_not_canceled <= 1.00
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 118.41] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |--- no_of_previous_bookings_not_canceled >  1.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 0.00] class: 0
|   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 11.50
|   |   |   |   |   |   |   |   |   |--- weights: [31.31, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  11.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [5.96, 9.11] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  75.07
|   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |--- weights: [59.64, 3.04] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.49, 16.70] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 86.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 16.70] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  86.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [8.95, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [44.73, 4.55] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  22.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |--- arrival_date <= 11.50
|   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |--- weights: [16.40, 39.47] class: 1
|   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |--- weights: [20.13, 6.07] class: 0
|   |   |   |   |   |   |--- arrival_date >  11.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 102.09
|   |   |   |   |   |   |   |   |--- weights: [5.22, 144.22] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  102.09
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 109.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 16.70] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [33.55, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  109.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 124.25
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.98, 75.91] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  124.25
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 3.04] class: 0
|   |   |   |   |--- lead_time >  117.50
|   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |--- arrival_date <= 7.50
|   |   |   |   |   |   |   |--- weights: [38.02, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_date >  7.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 65.38
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  65.38
|   |   |   |   |   |   |   |   |   |--- weights: [24.60, 3.04] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |   |   |--- arrival_date <= 28.00
|   |   |   |   |   |   |   |   |   |--- weights: [14.91, 72.87] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  28.00
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 1.52] class: 0
|   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |--- weights: [84.25, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |--- lead_time <= 125.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 90.85
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 87.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [13.42, 13.66] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  87.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 15.18] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  90.85
|   |   |   |   |   |   |   |   |   |--- weights: [10.44, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  125.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 19.50
|   |   |   |   |   |   |   |   |   |--- weights: [58.15, 18.22] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  19.50
|   |   |   |   |   |   |   |   |   |--- weights: [61.88, 1.52] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- lead_time <= 13.50
|   |   |   |   |--- avg_price_per_room <= 99.44
|   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |--- weights: [92.45, 0.00] class: 0
|   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 70.05
|   |   |   |   |   |   |   |   |   |--- weights: [31.31, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  70.05
|   |   |   |   |   |   |   |   |   |--- lead_time <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [38.77, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |--- lead_time >  5.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [34.30, 40.99] class: 1
|   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 19.74] class: 1
|   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 2.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 74.21
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  74.21
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  2.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 10.63] class: 1
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |   |   |   |--- weights: [155.07, 6.07] class: 0
|   |   |   |   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- weights: [3.73, 10.63] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [7.46, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  99.44
|   |   |   |   |   |--- lead_time <= 3.50
|   |   |   |   |   |   |--- avg_price_per_room <= 202.67
|   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |--- weights: [63.37, 30.36] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 20.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [115.56, 12.14] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  20.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [28.33, 3.04] class: 0
|   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 6.07] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  202.67
|   |   |   |   |   |   |   |--- weights: [0.75, 22.77] class: 1
|   |   |   |   |   |--- lead_time >  3.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 119.25
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 118.50
|   |   |   |   |   |   |   |   |   |--- weights: [18.64, 59.21] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  118.50
|   |   |   |   |   |   |   |   |   |--- weights: [8.20, 1.52] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  119.25
|   |   |   |   |   |   |   |   |--- weights: [34.30, 171.55] class: 1
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- weights: [26.09, 1.52] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 14.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 36.43] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  14.00
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 208.67
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  208.67
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [15.66, 0.00] class: 0
|   |   |   |--- lead_time >  13.50
|   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 71.92
|   |   |   |   |   |   |--- avg_price_per_room <= 59.43
|   |   |   |   |   |   |   |--- lead_time <= 84.50
|   |   |   |   |   |   |   |   |--- weights: [50.70, 7.59] class: 0
|   |   |   |   |   |   |   |--- lead_time >  84.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.00
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 131.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 15.18] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  131.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- weights: [10.44, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  59.43
|   |   |   |   |   |   |   |--- lead_time <= 25.50
|   |   |   |   |   |   |   |   |--- weights: [20.88, 6.07] class: 0
|   |   |   |   |   |   |   |--- lead_time >  25.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.34
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [15.66, 78.94] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 102.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  102.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.34
|   |   |   |   |   |   |   |   |   |--- weights: [11.18, 0.00] class: 0
|   |   |   |   |   |--- avg_price_per_room >  71.92
|   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |--- lead_time <= 65.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 120.45
|   |   |   |   |   |   |   |   |   |--- weights: [79.77, 9.11] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  120.45
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 12.14] class: 1
|   |   |   |   |   |   |   |--- lead_time >  65.50
|   |   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 <= 0.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [16.40, 47.06] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 63.76] class: 1
|   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 104.31
|   |   |   |   |   |   |   |   |--- lead_time <= 25.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [16.40, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [38.77, 118.41] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  25.50
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [39.51, 185.21] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [73.81, 411.41] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  104.31
|   |   |   |   |   |   |   |   |--- arrival_month <= 10.50
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 5 <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 195.30
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 9
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  195.30
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 138.15] class: 1
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 5 >  0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 9.11] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  10.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 168.06
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 22.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  22.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [17.15, 83.50] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  168.06
|   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 6.07] class: 0
|   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |--- weights: [48.46, 1.52] class: 0
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |--- lead_time <= 102.50
|   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |--- weights: [697.09, 9.11] class: 0
|   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |--- lead_time <= 63.00
|   |   |   |   |   |   |   |--- weights: [15.66, 1.52] class: 0
|   |   |   |   |   |   |--- lead_time >  63.00
|   |   |   |   |   |   |   |--- weights: [0.00, 7.59] class: 1
|   |   |   |   |--- lead_time >  102.50
|   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- weights: [31.31, 13.66] class: 0
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- weights: [0.75, 6.07] class: 1
|   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |--- weights: [44.73, 3.04] class: 0
|   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |--- lead_time <= 8.50
|   |   |   |   |   |--- lead_time <= 4.50
|   |   |   |   |   |   |--- no_of_week_nights <= 10.00
|   |   |   |   |   |   |   |--- weights: [498.03, 40.99] class: 0
|   |   |   |   |   |   |--- no_of_week_nights >  10.00
|   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |--- lead_time >  4.50
|   |   |   |   |   |   |--- arrival_date <= 13.50
|   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |--- weights: [58.90, 36.43] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |--- weights: [33.55, 1.52] class: 0
|   |   |   |   |   |   |--- arrival_date >  13.50
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |--- weights: [123.76, 9.11] class: 0
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 126.33
|   |   |   |   |   |   |   |   |   |--- weights: [32.80, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  126.33
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 13.66] class: 1
|   |   |   |   |--- lead_time >  8.50
|   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |--- avg_price_per_room <= 118.55
|   |   |   |   |   |   |   |--- lead_time <= 61.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [70.08, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [126.74, 1.52] class: 0
|   |   |   |   |   |   |   |--- lead_time >  61.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 57.69] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 66.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  66.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.93
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [54.43, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.93
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 10
|   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |--- avg_price_per_room >  118.55
|   |   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 19.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 177.15
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  177.15
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 6.07] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  19.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 121.20
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [18.64, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  121.20
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 55.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  55.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [11.93, 10.63] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [37.28, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 119.20
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 28.84] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  119.20
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 12
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 100.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [49.95, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  100.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 18.22] class: 1
|   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |--- weights: [134.20, 1.52] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |--- weights: [1585.04, 0.00] class: 0
|   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- no_of_week_nights <= 9.50
|   |   |   |   |   |   |   |--- lead_time <= 6.50
|   |   |   |   |   |   |   |   |--- weights: [32.06, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  6.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  5.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 93.09
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  93.09
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [77.54, 27.33] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [19.38, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_week_nights >  9.50
|   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [52.19, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |--- avg_price_per_room <= 202.95
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.49, 9.11] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |--- weights: [8.20, 3.04] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- lead_time <= 150.50
|   |   |   |   |   |   |   |   |   |--- weights: [175.20, 28.84] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  150.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  202.95
|   |   |   |   |   |   |   |--- weights: [0.00, 10.63] class: 1
|   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |--- avg_price_per_room <= 153.15
|   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 2 <= 0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.12
|   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.12
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 90.42
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 7.59] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  90.42
|   |   |   |   |   |   |   |   |   |   |--- weights: [64.12, 60.72] class: 0
|   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 2 >  0.50
|   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  153.15
|   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |--- weights: [67.10, 0.00] class: 0
|--- lead_time >  151.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- no_of_special_requests <= 0.50
|   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |--- lead_time <= 163.50
|   |   |   |   |   |   |--- arrival_month <= 5.00
|   |   |   |   |   |   |   |--- weights: [2.98, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  5.00
|   |   |   |   |   |   |   |--- weights: [0.75, 24.29] class: 1
|   |   |   |   |   |--- lead_time >  163.50
|   |   |   |   |   |   |--- lead_time <= 341.00
|   |   |   |   |   |   |   |--- lead_time <= 173.00
|   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |--- weights: [46.97, 9.11] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 13.66] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  173.00
|   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |--- weights: [188.62, 7.59] class: 0
|   |   |   |   |   |   |--- lead_time >  341.00
|   |   |   |   |   |   |   |--- weights: [13.42, 27.33] class: 1
|   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |--- avg_price_per_room <= 2.50
|   |   |   |   |   |   |--- lead_time <= 285.50
|   |   |   |   |   |   |   |--- weights: [8.20, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  285.50
|   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |--- avg_price_per_room >  2.50
|   |   |   |   |   |   |--- weights: [0.75, 97.16] class: 1
|   |   |   |--- no_of_adults >  1.50
|   |   |   |   |--- avg_price_per_room <= 82.47
|   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |--- weights: [2.98, 282.37] class: 1
|   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |--- lead_time <= 244.00
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 166.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  166.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 57.69] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [17.89, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 12.14] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [75.30, 12.14] class: 0
|   |   |   |   |   |   |   |--- lead_time >  244.00
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- weights: [25.35, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 80.38
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 264.15] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  80.38
|   |   |   |   |   |   |   |   |   |   |--- weights: [7.46, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |--- weights: [46.22, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  82.47
|   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |--- lead_time <= 324.50
|   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [7.46, 986.78] class: 1
|   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 10.63] class: 1
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 19.74] class: 1
|   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  324.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 89.00
|   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  89.00
|   |   |   |   |   |   |   |   |--- weights: [0.75, 13.66] class: 1
|   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |--- no_of_special_requests >  0.50
|   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |--- lead_time <= 180.50
|   |   |   |   |   |--- lead_time <= 159.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- weights: [1.49, 7.59] class: 1
|   |   |   |   |   |--- lead_time >  159.50
|   |   |   |   |   |   |--- arrival_date <= 1.50
|   |   |   |   |   |   |   |--- weights: [1.49, 3.04] class: 1
|   |   |   |   |   |   |--- arrival_date >  1.50
|   |   |   |   |   |   |   |--- weights: [35.79, 1.52] class: 0
|   |   |   |   |--- lead_time >  180.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |   |   |--- weights: [7.46, 206.46] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |--- avg_price_per_room <= 76.48
|   |   |   |   |   |   |   |--- weights: [46.97, 4.55] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  76.48
|   |   |   |   |   |   |   |--- no_of_week_nights <= 6.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 233.00
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 152.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.49, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  152.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- lead_time >  233.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 19.74] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 15.18] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 269.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  269.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |--- no_of_week_nights >  6.50
|   |   |   |   |   |   |   |   |--- weights: [4.47, 13.66] class: 1
|   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |--- arrival_date <= 14.50
|   |   |   |   |   |   |   |--- weights: [8.20, 3.04] class: 0
|   |   |   |   |   |   |--- arrival_date >  14.50
|   |   |   |   |   |   |   |--- weights: [11.18, 31.88] class: 1
|   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |--- lead_time <= 348.50
|   |   |   |   |   |   |--- weights: [106.61, 3.04] class: 0
|   |   |   |   |   |--- lead_time >  348.50
|   |   |   |   |   |   |--- weights: [5.96, 4.55] class: 0
|   |--- avg_price_per_room >  100.04
|   |   |--- arrival_month <= 11.50
|   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |--- weights: [0.00, 3200.19] class: 1
|   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |--- arrival_month >  11.50
|   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |--- weights: [35.04, 0.00] class: 0
|   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |--- weights: [3.73, 22.77] class: 1


# Plot the feature importances for the post-pruned tree.

importances = best_model.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(12, 12))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()


# Summarize the performance measures for all 3 decision trees on the training data.

models_train_comp_df = pd.concat(
    [
        decision_tree_perf_train.T,
        decision_tree_tune_perf_train.T,
        decision_tree_post_perf_train.T,
    ],
    axis=1,
)
models_train_comp_df.columns = [
    "Decision Tree without pruning",
    "Decision Tree (Pre-Pruning)",
    "Decision Tree (Post-Pruning)",
]
print("Training performance comparison:")
models_train_comp_df

Training performance comparison:


# Summarize the performance measures for all 3 decision trees on the test data.

models_test_comp_df = pd.concat(
    [
        decision_tree_perf_test.T,
        decision_tree_tune_perf_test.T,
        decision_tree_post_test.T,
    ],
    axis=1,
)
models_test_comp_df.columns = [
    "Decision Tree without pruning",
    "Decision Tree (Pre-Pruning)",
    "Decision Tree (Post-Pruning)",
]
print("Test set performance comparison:")
models_test_comp_df

Test set performance comparison:


# Import libraries for data manipulation.
import pandas as pd
import numpy as np

# Import libraries for data visualization.
import matplotlib.pyplot as plt
import seaborn as sns

# Import library to split data.
from sklearn.model_selection import train_test_split

# Import predictive model-building libraries.
from sklearn import tree
from sklearn.tree import DecisionTreeClassifier

# Import functions to evaluate model performance.
from sklearn import metrics
from sklearn.metrics import confusion_matrix, classification_report
from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score

# Import GridSearch to tune different models.
from sklearn.model_selection import GridSearchCV

# Import ensemble methods.
from sklearn.ensemble import BaggingClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import StackingClassifier
from xgboost import XGBClassifier

# Import libraries to ignore irrelevant warnings.
import warnings
warnings.filterwarnings('ignore')


# Set the precision of floating numbers to 3 decimal points.
pd.set_option("display.float_format", lambda x: "%.3f" % x)


# Mount Google Drive.

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive


# Load the data set.

data = pd.read_csv('/content/drive/My Drive/Data science/Data sets/EasyVisa.csv')


# Use .shape attribute to display the number of rows & columns in the data set.

data.shape

(25480, 12)


# Display a sample of 5 rows from the data set to get a general idea of the information & make sure it is loaded properly.

data.sample(5)


# Check the number of unique values in the case_id column to see if it should be dropped.

data.case_id.nunique()

25480


# All the case_id values are unique, so the column can be dropped as it will not aid in analysis.

data1 = data.drop('case_id', axis=1)


# Use .info() method to check the non-null counts and data types of each column.

data1.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 25480 entries, 0 to 25479
Data columns (total 11 columns):
 #   Column                 Non-Null Count  Dtype  
---  ------                 --------------  -----  
 0   continent              25480 non-null  object 
 1   education_of_employee  25480 non-null  object 
 2   has_job_experience     25480 non-null  object 
 3   requires_job_training  25480 non-null  object 
 4   no_of_employees        25480 non-null  int64  
 5   yr_of_estab            25480 non-null  int64  
 6   region_of_employment   25480 non-null  object 
 7   prevailing_wage        25480 non-null  float64
 8   unit_of_wage           25480 non-null  object 
 9   full_time_position     25480 non-null  object 
 10  case_status            25480 non-null  object 
dtypes: float64(1), int64(2), object(8)
memory usage: 2.1+ MB


# Make a copy of the data to convert year established into years since established for improved statistical analysis.

data2 = data1.copy()
data2['yrs_since_estab'] = 2022-data2['yr_of_estab']
data2 = data2.drop(['yr_of_estab'], axis=1)


# Check the statistical summary for the numeric columns

data2.describe().T


# Check the number of rows where the number of employees is negative.

data2[data2['no_of_employees']<0].shape[0]

33


# Replace all values in the column no_of_employees with their absolute values.

data2["no_of_employees"] = np.abs(data2["no_of_employees"])


# Double check the number of rows where the number of employees is negative.

data2[data2['no_of_employees']<0].shape[0]

0


# Check for duplicated values.

data2.duplicated().sum()

0


# Use a countplot to visualize the distribution of continents.

plt.figure(figsize=(15, 5))
plt.title('Countplot: Continents')
sns.countplot(data=data2, x='continent', order=data2['continent'].value_counts().reset_index()['index'].tolist())
plt.xlabel("Continent")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of education level.

plt.title('Countplot: Education Level')
sns.countplot(data=data2, x='education_of_employee', order=['High School',"Bachelor's","Master's","Doctorate"])
plt.xlabel("Education Level")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of work experience.

plt.title('Countplot: Work Experience')
sns.countplot(data=data2, x='has_job_experience')
plt.xlabel("Work Experience")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of those who require job training.

plt.title('Countplot: Requiring Job Training')
sns.countplot(data=data2, x='requires_job_training')
plt.xlabel("Requires Job Training")
plt.ylabel('Count');


# Create a user-defined function to display histogram & boxplot together for numeric variables.

def histogram_boxplot(data, feature, figsize=(18, 5), kde=True, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (18,5))
    kde: whether to show the density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows=2,  # Number of rows of the subplot grid= 2
        sharex=True,  # x-axis will be shared among all subplots
        gridspec_kw={"height_ratios": (0.3, 0.7)},
        figsize=figsize,
    )  # creating the 2 subplots
    sns.boxplot(
        data=data, x=feature, ax=ax_box2, showmeans=True, color="violet"
    )  # boxplot will be created and a triangle will indicate the mean value of the column
    sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2, bins=bins
    ) if bins else sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2
    )  # For histogram
    ax_hist2.axvline(
        data[feature].mean(), color="green", linestyle="--"
    )  # Add mean to the histogram
    ax_hist2.axvline(
        data[feature].median(), color="black", linestyle="-"
    )  # Add median to the histogram


# Visualize histogram & boxplot for number of employees.

histogram_boxplot(data=data2, feature='no_of_employees')


# Visualize histogram & boxplot for years since established.

histogram_boxplot(data=data2, feature='yrs_since_estab')


# Use a countplot to visualize the distribution of region of employment.

plt.title('Countplot: Region of Employment')
sns.countplot(data=data2, x='region_of_employment', order=data2['region_of_employment'].value_counts().reset_index()['index'].tolist())
plt.xlabel("Region of Employment")
plt.ylabel('Count');


# Visualize histogram & boxplot for prevailing wage.

histogram_boxplot(data=data2, feature='prevailing_wage')


# Use a countplot to visualize the distribution of unit of wage.

plt.title('Countplot: Unit of Wage')
sns.countplot(data=data2, x='unit_of_wage', order=['Hour','Week','Month','Year'])
plt.xlabel("Unit of Wage")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of full time positions.

plt.title('Countplot: Full Time Position')
sns.countplot(data=data2, x='full_time_position')
plt.xlabel("Full Time Position")
plt.ylabel('Count');


# Use a countplot to visualize the distribution of case status.

plt.title('Countplot: Case Status')
sns.countplot(data=data2, x='case_status')
plt.xlabel("Case Status")
plt.ylabel('Count');


# Make a new DataFrame to encode booking status to 1 for Certified visasa and 0 for Denied.

data3 = data2.copy()
data3['case_status'] = data["case_status"].apply(lambda x: 1 if x == "Certified" else 0)


# Use heatmap to visualize correlation between numeric variables.

plt.figure(figsize=(10, 8))
sns.heatmap(data3.corr(), annot=True);


# Use countplot with hue parameter to visualize differences in visa certification status across different regions.

plt.title('Countplot: Visa Status by Region of Employment')
sns.countplot(data=data2, x='region_of_employment', hue='case_status', order=['Midwest','South','Northeast','West','Island'])
plt.xlabel("Region")
plt.ylabel('Count');


# Create a DataFrame to display % of visas certified for each region of employment.

cert = data2[data2['case_status']=='Certified']['region_of_employment'].value_counts().rename('certified').reset_index()
totals = data2['region_of_employment'].value_counts().rename('total').reset_index()
cert_pct = pd.merge(cert,totals)
cert_pct.rename(columns={'index':'region'}, inplace=True)
cert_pct['pct_cert'] = cert_pct['certified']/cert_pct['total']*100
cert_pct = cert_pct.sort_values(by='pct_cert', ascending=False).reset_index(drop=True)
cert_pct


# Use countplot with hue parameter to visualize differences in visa certification status based on job training requirements.

plt.title('Countplot: Visa Status by Job Training Requirement')
sns.countplot(data=data2, x='requires_job_training', hue='case_status')
plt.xlabel("Requires Job Training")
plt.ylabel('Count');


# Create a DataFrame to display % of visas certified based on job training requirement.

cert = data2[data2['case_status']=='Certified']['requires_job_training'].value_counts().rename('certified').reset_index()
totals = data2['requires_job_training'].value_counts().rename('total').reset_index()
cert_pct = pd.merge(cert,totals)
cert_pct.rename(columns={'index':'training required'}, inplace=True)
cert_pct['pct_cert'] = cert_pct['certified']/cert_pct['total']*100
cert_pct = cert_pct.sort_values(by='pct_cert', ascending=False).reset_index(drop=True)
cert_pct


# Use countplot with hue parameter to visualize differences in visa certification status for those with and without full time positions.

plt.title('Countplot: Visa Status by Full Time Position')
sns.countplot(data=data2, x='full_time_position', hue='case_status')
plt.xlabel("Full Time Position")
plt.ylabel('Count');


# Create a DataFrame to display % of visas certified based on job training requirement.

cert = data2[data2['case_status']=='Certified']['full_time_position'].value_counts().rename('certified').reset_index()
totals = data2['full_time_position'].value_counts().rename('total').reset_index()
cert_pct = pd.merge(cert,totals)
cert_pct.rename(columns={'index':'full time'}, inplace=True)
cert_pct['pct_cert'] = cert_pct['certified']/cert_pct['total']*100
cert_pct = cert_pct.sort_values(by='pct_cert', ascending=False).reset_index(drop=True)
cert_pct


# Visualize boxplot of years since established based on case status.

plt.figure(figsize=(18, 5))
plt.title('Boxplot: Visa Status by Years Since Established')
sns.boxplot(data=data2, x='yrs_since_estab', y='case_status')
plt.xlabel("Years Since Established")
plt.ylabel("Case Status");


# Visualize boxplot of number of employees based on case status.

plt.figure(figsize=(18, 5))
plt.title('Boxplot: Visa Status by Number of Employees')
sns.boxplot(data=data2, x='no_of_employees', y='case_status')
plt.xlabel("Number of Employees")
plt.ylabel("Case Status");


# Use countplot with hue parameter to visualize differences in visa certification status across different education levels.

plt.title('Countplot: Visa Status by Education Level')
sns.countplot(data=data2, x='education_of_employee', hue='case_status', order=['High School',"Bachelor's","Master's","Doctorate"])
plt.legend(loc='upper left')
plt.xlabel("Employee Education Level")
plt.ylabel('Count');


# Create a DataFrame to display % of visas certified for each education level.

cert = data2[data2['case_status']=='Certified']['education_of_employee'].value_counts().rename('certified').reset_index()
totals = data2['education_of_employee'].value_counts().rename('total').reset_index()
cert_pct = pd.merge(cert,totals)
cert_pct.rename(columns={'index':'education level'}, inplace=True)
cert_pct['pct_cert'] = cert_pct['certified']/cert_pct['total']*100
cert_pct = cert_pct.sort_values(by='pct_cert', ascending=False).reset_index(drop=True)
cert_pct


# Use countplot with hue parameter to visualize differences in visa certification status across different continents.

plt.figure(figsize=(15, 5))
plt.title('Countplot: Visa Status by Continent')
sns.countplot(data=data2, x='continent', hue='case_status', order=['Europe','Africa','Asia','Oceania','North America','South America'])
plt.xlabel("Continent")
plt.ylabel('Count');


# Create a DataFrame to display % of visas certified for each continent.

cert = data2[data2['case_status']=='Certified']['continent'].value_counts().rename('certified').reset_index()
totals = data2['continent'].value_counts().rename('total').reset_index()
cert_pct = pd.merge(cert,totals)
cert_pct.rename(columns={'index':'continent'}, inplace=True)
cert_pct['pct_cert'] = cert_pct['certified']/cert_pct['total']*100
cert_pct = cert_pct.sort_values(by='pct_cert', ascending=False).reset_index(drop=True)
cert_pct


# Use countplot with hue parameter to visualize differences in visa certification status for those with and without work experience.

plt.title('Countplot: Visa Status by Work Experience')
sns.countplot(data=data2, x='has_job_experience', hue='case_status')
plt.xlabel("Work Experience")
plt.ylabel('Count');


# Create a DataFrame to display % of visas certified for people with work experience vs. those without work experience.

cert = data2[data2['case_status']=='Certified']['has_job_experience'].value_counts().rename('certified').reset_index()
totals = data2['has_job_experience'].value_counts().rename('total').reset_index()
cert_pct = pd.merge(cert,totals)
cert_pct.rename(columns={'index':'job experience'}, inplace=True)
cert_pct['pct_cert'] = cert_pct['certified']/cert_pct['total']*100
cert_pct = cert_pct.sort_values(by='pct_cert', ascending=False).reset_index(drop=True)
cert_pct


# Use countplot with hue parameter to visualize differences in visa certification status across different wage payment intervals.

plt.title('Countplot: Visa Status by Unit of Wage')
sns.countplot(data=data2, x='unit_of_wage', hue='case_status', order=['Hour','Week','Month','Year'])
plt.xlabel("Unit of Wage")
plt.ylabel('Count');


# Create a DataFrame to display % of visas certified across different wage payment intervals.

cert = data2[data2['case_status']=='Certified']['unit_of_wage'].value_counts().rename('certified').reset_index()
totals = data2['unit_of_wage'].value_counts().rename('total').reset_index()
cert_pct = pd.merge(cert,totals)
cert_pct.rename(columns={'index':'unit of wage'}, inplace=True)
cert_pct['pct_cert'] = cert_pct['certified']/cert_pct['total']*100
cert_pct = cert_pct.sort_values(by='pct_cert', ascending=False).reset_index(drop=True)
cert_pct


# Visualize boxplot of prevailing wage based on case status.

plt.figure(figsize=(18, 5))
plt.title('Boxplot: Visa Status by Prevailing Wage')
sns.boxplot(data=data2, x='prevailing_wage', y='case_status')
plt.xlabel("Prevailing Wage")
plt.ylabel("Case Status");


# Check for null values in the data.

data2.isnull().sum()

continent                0
education_of_employee    0
has_job_experience       0
requires_job_training    0
no_of_employees          0
region_of_employment     0
prevailing_wage          0
unit_of_wage             0
full_time_position       0
case_status              0
yrs_since_estab          0
dtype: int64


# Use boxplot to visualize outliers.

numeric_columns = data2.select_dtypes(include=np.number).columns.tolist()


plt.figure(figsize=(15, 12))

for i, variable in enumerate(numeric_columns):
    plt.subplot(4, 4, i + 1)
    plt.boxplot(data2[variable], whis=1.5)
    plt.tight_layout()
    plt.title(variable)

plt.show()


# Separate the x & y variables and split each into training and testing sets.

X = data3.drop(['case_status'],axis=1)
X = pd.get_dummies(X,drop_first=True)
y = data3['case_status']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1,stratify=y)
print(X_train.shape, X_test.shape)

(17836, 21) (7644, 21)


# Print the features of the training and test sets.

print("Percentage of classes in training set:")
print(y_train.value_counts(normalize=True))
print("Percentage of classes in test set:")
print(y_test.value_counts(normalize=True))

Percentage of classes in training set:
1   0.668
0   0.332
Name: case_status, dtype: float64
Percentage of classes in test set:
1   0.668
0   0.332
Name: case_status, dtype: float64


# Create a user-defined function to display a DataFrame of model performance metrics.

def model_performance_classification_sklearn(model, predictors, target):
    """
    Function to compute different metrics to check classification model performance

    model: classifier
    predictors: independent variables
    target: dependent variable
    """

    # predicting using the independent variables
    pred = model.predict(predictors)

    acc = accuracy_score(target, pred)  # to compute accuracy
    recall = recall_score(target, pred)  # to compute recall
    precision = precision_score(target, pred)  # to compute precision
    f1 = f1_score(target, pred)  # to compute F1-score

    # creating a dataframe of metrics
    df_perf = pd.DataFrame(
        {
            "Accuracy": acc,
            "Recall": recall,
            "Precision": precision,
            "F1": f1,
        },
        index=[0],
    )

    return df_perf


# Create a user-defined function to display a confusion matrix for classification models.

def confusion_matrix_sklearn(model, predictors, target):
    """
    To plot the confusion_matrix with percentages

    model: classifier
    predictors: independent variables
    target: dependent variable
    """
    y_pred = model.predict(predictors)
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ["{0:0.0f}".format(item) + "\n{0:.2%}".format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")
    plt.ylabel("True label")
    plt.xlabel("Predicted label")


# Fit the initial decision tree model.

dtree = DecisionTreeClassifier(criterion='gini',random_state=1)
dtree.fit(X_train, y_train)

DecisionTreeClassifier(random_state=1)


# Display the confusion matrix for the initial decision tree on the training data.

confusion_matrix_sklearn(dtree, X_train, y_train)


# Display the DataFrame of performance measures for the initial decision tree on the training data.

dtree_model_train_perf=model_performance_classification_sklearn(dtree, X_train, y_train)
print("Training performance \n",dtree_model_train_perf)

Training performance 
    Accuracy  Recall  Precision    F1
0     1.000   1.000      1.000 1.000


# Display the confusion matrix for the initial decision tree on the test data.

confusion_matrix_sklearn(dtree, X_test, y_test)


# Display the DataFrame of performance measures for the initial decision tree on the test data.

dtree_model_test_perf=model_performance_classification_sklearn(dtree, X_test, y_test)
print("Test performance \n",dtree_model_test_perf)

Test performance 
    Accuracy  Recall  Precision    F1
0     0.658   0.738      0.747 0.742


# Fit the initial bagging classifier model.

bagging = BaggingClassifier(random_state=1)
bagging.fit(X_train,y_train)

BaggingClassifier(random_state=1)


# Display the confusion matrix for the initial bagging classifier model on the training data.

confusion_matrix_sklearn(bagging, X_train, y_train)


# Display the DataFrame of performance measures for the initial bagging classifier model on the training data.

bagging_model_train_perf=model_performance_classification_sklearn(bagging, X_train, y_train)
print("Training performance \n",bagging_model_train_perf)

Training performance 
    Accuracy  Recall  Precision    F1
0     0.985   0.986      0.992 0.989


# Display the confusion matrix for the initial bagging classifier model on the test data.

confusion_matrix_sklearn(bagging, X_test, y_test)


# Display the DataFrame of performance measures for the initial bagging classifier model on the test data.

bagging_model_test_perf=model_performance_classification_sklearn(bagging, X_test, y_test)
print("Testing performance \n",bagging_model_test_perf)

Testing performance 
    Accuracy  Recall  Precision    F1
0     0.695   0.768      0.774 0.771


# Fit the initial random forest model.

rf = RandomForestClassifier(random_state=1)
rf.fit(X_train,y_train)

RandomForestClassifier(random_state=1)


# Display the confusion matrix for the initial random forest model on the training data.

confusion_matrix_sklearn(rf,X_train,y_train)


# Display the DataFrame of performance measures for the initial random forest model on the training data.

rf_model_train_perf=model_performance_classification_sklearn(rf,X_train,y_train)
print("Training performance \n",rf_model_train_perf)

Training performance 
    Accuracy  Recall  Precision    F1
0     1.000   1.000      1.000 1.000


# Display the confusion matrix for the initial random forest model on the test data.

confusion_matrix_sklearn(rf,X_test,y_test)


# Display the DataFrame of performance measures for the initial random forest model on the test data.

rf_model_test_perf=model_performance_classification_sklearn(rf,X_test,y_test)
print("Test performance \n",rf_model_test_perf)

Test performance 
    Accuracy  Recall  Precision    F1
0     0.721   0.834      0.768 0.799


np.arange(5, 16, 5)

array([ 5, 10, 15])


# Use GridSearch to perform hyperparameter tuning on the decision tree model.

# Choose the type of classifier. 
dtree_estimator = DecisionTreeClassifier(random_state=1)

# Grid of parameters to choose from
parameters = {'max_depth': [5, 10, 15], 
              'min_samples_leaf': [2, 5, 7],
              'max_leaf_nodes' : [2, 3, 5],
              'min_impurity_decrease': [0.0001,0.1]
             }

# Type of scoring used to compare parameter combinations
scorer = metrics.make_scorer(metrics.recall_score)

# Run the grid search
grid_obj = GridSearchCV(dtree_estimator, parameters, scoring=scorer)
grid_obj = grid_obj.fit(X_train, y_train)

# Set the clf to the best combination of parameters
dtree_estimator = grid_obj.best_estimator_

# Fit the best algorithm to the data. 
dtree_estimator.fit(X_train, y_train)

DecisionTreeClassifier(max_depth=5, max_leaf_nodes=2, min_impurity_decrease=0.1,
                       min_samples_leaf=2, random_state=1)


# Display the confusion matrix for the tuned decision tree on the training data.

confusion_matrix_sklearn(dtree_estimator, X_train, y_train)


# Display the DataFrame of performance measures for the tuned decision tree on the training data.

dtree_estimator_model_train_perf=model_performance_classification_sklearn(dtree_estimator, X_train,y_train)
print("Training performance \n",dtree_estimator_model_train_perf)

Training performance 
    Accuracy  Recall  Precision    F1
0     0.668   1.000      0.668 0.801


# Display the confusion matrix for the tuned decision tree on the test data.

confusion_matrix_sklearn(dtree_estimator, X_test,y_test)


# Display the DataFrame of performance measures for the tuned decision tree on the test data.

dtree_estimator_model_test_perf=model_performance_classification_sklearn(dtree_estimator, X_test, y_test)
print("Testing performance \n",dtree_estimator_model_test_perf)

Testing performance 
    Accuracy  Recall  Precision    F1
0     0.668   1.000      0.668 0.801


# Use GridSearch to tune the bagging classifier model.

cl1 = DecisionTreeClassifier(random_state=1)
param_grid = {'base_estimator':[cl1],
              'n_estimators':[15,51,101],
              'max_features': [0.7,0.9,1]
             }

grid = GridSearchCV(BaggingClassifier(random_state=1,bootstrap=True), param_grid=param_grid, scoring = 'recall', cv = 5)
grid.fit(X_train, y_train)

bagging_estimator = grid.best_estimator_
bagging_estimator.fit(X_train,y_train)

BaggingClassifier(base_estimator=DecisionTreeClassifier(random_state=1),
                  max_features=1, n_estimators=101, random_state=1)


# Display the confusion matrix for the tuned bagging classifier on the train data.

confusion_matrix_sklearn(bagging_estimator, X_train,y_train)


# Display the DataFrame of performance measures for the tuned bagging classifier on the training data.

bagging_estimator_model_train_perf=model_performance_classification_sklearn(bagging_estimator, X_train,y_train)
print("Training performance \n",bagging_estimator_model_train_perf)

Training performance 
    Accuracy  Recall  Precision    F1
0     0.668   1.000      0.668 0.801


# Display the confusion matrix for the tuned bagging classifier on the test data.

confusion_matrix_sklearn(bagging_estimator, X_test,y_test)


# Display the DataFrame of performance measures for the tuned bagging classifier on the test data.

bagging_estimator_model_test_perf=model_performance_classification_sklearn(bagging_estimator, X_test, y_test)
print("Testing performance \n",bagging_estimator_model_test_perf)

Testing performance 
    Accuracy  Recall  Precision    F1
0     0.668   1.000      0.668 0.801


# Choose the type of classifier. 
rf_estimator = RandomForestClassifier(random_state=1)

# Grid of parameters to choose from
parameters = {  
        "n_estimators": [25, 75, 100],
        "min_samples_leaf": np.arange(1, 4),
        "max_features": [0.7,'log2','auto'],
        "max_samples": [0.7,0.9,None],
}

# Run the grid search
grid_obj = GridSearchCV(rf_estimator, parameters, scoring='recall',cv=5)
grid_obj = grid_obj.fit(X_train, y_train)

# Set the clf to the best combination of parameters
rf_estimator = grid_obj.best_estimator_

# Fit the best algorithm to the data. 
rf_estimator.fit(X_train, y_train)

RandomForestClassifier(max_features='log2', max_samples=0.7, min_samples_leaf=3,
                       random_state=1)


# Display the confusion matrix for the tuned random forest model on the training data.

confusion_matrix_sklearn(rf_estimator, X_train,y_train)


# Display the DataFrame of performance measures for the tuned random forest on the training data.

rf_estimator_model_train_perf=model_performance_classification_sklearn(rf_estimator, X_train,y_train)
print("Training performance \n",rf_estimator_model_train_perf)

Training performance 
    Accuracy  Recall  Precision    F1
0     0.823   0.928      0.828 0.875


# Display the confusion matrix for the tuned random forest model on the test data.

confusion_matrix_sklearn(rf_estimator, X_test,y_test)


# Display the DataFrame of performance measures for the tuned random forest on the test data.

rf_estimator_model_test_perf=model_performance_classification_sklearn(rf_estimator, X_test, y_test)
print("Testing performance \n",rf_estimator_model_test_perf)

Testing performance 
    Accuracy  Recall  Precision    F1
0     0.740   0.871      0.770 0.817


# Fit the initial AdaBoost model.

ab_classifier = AdaBoostClassifier(random_state=1)
ab_classifier.fit(X_train,y_train)

AdaBoostClassifier(random_state=1)


# Display the confusion matrix for the initial AdaBoost model on the training data.

confusion_matrix_sklearn(ab_classifier,X_train,y_train)


# Display the DataFrame of performance measures for the initial AdaBoost model on the training data.

ab_classifier_model_train_perf=model_performance_classification_sklearn(ab_classifier,X_train,y_train)
print(ab_classifier_model_train_perf)

   Accuracy  Recall  Precision    F1
0     0.738   0.887      0.760 0.819


# Display the confusion matrix for the initial AdaBoost model on the test data.

confusion_matrix_sklearn(ab_classifier,X_test,y_test)


# Display the DataFrame of performance measures for the initial AdaBoost model on the test data.

ab_classifier_model_test_perf=model_performance_classification_sklearn(ab_classifier,X_test,y_test)
print(ab_classifier_model_test_perf)

   Accuracy  Recall  Precision    F1
0     0.733   0.885      0.757 0.816


#Fit the initial GradientBoost model.

gb_classifier = GradientBoostingClassifier(random_state=1)
gb_classifier.fit(X_train,y_train)

GradientBoostingClassifier(random_state=1)


# Display the confusion matrix for the initial GradientBoost model on the training data.

confusion_matrix_sklearn(gb_classifier,X_train,y_train)


# Display the DataFrame of performance measures for the initial GradientBoost model on the training data.

gb_classifier_model_train_perf=model_performance_classification_sklearn(gb_classifier,X_train,y_train)
print("Training performance:\n",gb_classifier_model_train_perf)

Training performance:
    Accuracy  Recall  Precision    F1
0     0.759   0.883      0.784 0.831


# Display the confusion matrix for the initial GradientBoost model on the test data.

confusion_matrix_sklearn(gb_classifier,X_test,y_test)


# Display the DataFrame of performance measures for the initial GradientBoost model on the test data.

gb_classifier_model_test_perf=model_performance_classification_sklearn(gb_classifier,X_test,y_test)
print("Testing performance:\n",gb_classifier_model_test_perf)

Testing performance:
    Accuracy  Recall  Precision    F1
0     0.745   0.873      0.774 0.820


# Use GridSearch to perform hyperparameter tuning on the AdaBoost model.

# Choose the type of classifier. 
abc_tuned = AdaBoostClassifier(random_state=1)

# Grid of parameters to choose from
parameters = {
    #Let's try different max_depth for base_estimator
    "base_estimator":[DecisionTreeClassifier(max_depth=1),DecisionTreeClassifier(max_depth=2)],
    "n_estimators": np.arange(40,110,20),
    "learning_rate":np.arange(0.1,0.7,0.1)
}

# Type of scoring used to compare parameter  combinations
scorer = metrics.make_scorer(metrics.recall_score)

# Run the grid search
grid_obj = GridSearchCV(abc_tuned, parameters, scoring=scorer,cv=5)
grid_obj = grid_obj.fit(X_train, y_train)

# Set the clf to the best combination of parameters
abc_tuned = grid_obj.best_estimator_

# Fit the best algorithm to the data.
abc_tuned.fit(X_train, y_train)

AdaBoostClassifier(base_estimator=DecisionTreeClassifier(max_depth=1),
                   learning_rate=0.1, n_estimators=40, random_state=1)


# Display the confusion matrix for the tuned AdaBoost model on the training data.

confusion_matrix_sklearn(abc_tuned,X_train,y_train)


# Display the DataFrame of performance measures for the tuned AdaBoost model on the training data.

abc_tuned_model_train_perf=model_performance_classification_sklearn(abc_tuned,X_train,y_train)
print(abc_tuned_model_train_perf)

   Accuracy  Recall  Precision    F1
0     0.718   0.936      0.723 0.816


# Display the confusion matrix for the tuned AdaBoost model on the test data.

confusion_matrix_sklearn(abc_tuned,X_test,y_test)


# Display the DataFrame of performance measures for the tuned AdaBoost model on the test data.

abc_tuned_model_test_perf=model_performance_classification_sklearn(abc_tuned,X_test,y_test)
print(abc_tuned_model_test_perf)

   Accuracy  Recall  Precision    F1
0     0.711   0.936      0.718 0.812


# Use GridSearch to perform hyperparameter tuning on the GradientBoost model.

# Choose the type of classifier. 
gbc_tuned = GradientBoostingClassifier(init=AdaBoostClassifier(random_state=1),random_state=1)

# Grid of parameters to choose from
parameters = {
    "n_estimators": [150,200,250],
    "subsample":[0.8,1],
    "max_features":[0.7,0.9],
    "learning_rate":np.arange(0.1,0.7,0.2)
}

# Type of scoring used to compare parameter combinations
scorer = metrics.make_scorer(metrics.recall_score)

# Run the grid search
grid_obj = GridSearchCV(gbc_tuned, parameters, scoring=scorer,cv=5)
grid_obj = grid_obj.fit(X_train, y_train)

# Set the clf to the best combination of parameters
gbc_tuned = grid_obj.best_estimator_

# Fit the best algorithm to the data.
gbc_tuned.fit(X_train, y_train)

GradientBoostingClassifier(init=AdaBoostClassifier(random_state=1),
                           max_features=0.9, n_estimators=200, random_state=1,
                           subsample=1)


# Display the confusion matrix for the tuned GradientBoost model on the training data.

confusion_matrix_sklearn(gbc_tuned,X_train,y_train)


# Display the DataFrame of performance measures for the tuned GradientBoost model on the training data.

gbc_tuned_model_train_perf=model_performance_classification_sklearn(gbc_tuned,X_train,y_train)
print("Training performance:\n",gbc_tuned_model_train_perf)

Training performance:
    Accuracy  Recall  Precision    F1
0     0.765   0.886      0.789 0.834


# Display the confusion matrix for the tuned GradientBoost model on the test data.

confusion_matrix_sklearn(gbc_tuned,X_test,y_test)


# Display the DataFrame of performance measures for the tuned GradientBoost model on the test data.

gbc_tuned_model_test_perf=model_performance_classification_sklearn(gbc_tuned,X_test,y_test)
print("Testing performance:\n",gbc_tuned_model_test_perf)

Testing performance:
    Accuracy  Recall  Precision    F1
0     0.746   0.874      0.774 0.821


estimators = [('Random Forest',rf_estimator), ('Gradient Boosting',gbc_tuned), ('AdaBoost',ab_classifier)]

final_estimator = XGBClassifier(random_state=1, eval_metric='logloss')

stacking_classifier= StackingClassifier(estimators=estimators,final_estimator=final_estimator)

stacking_classifier.fit(X_train,y_train)

StackingClassifier(estimators=[('Random Forest',
                                RandomForestClassifier(max_features='log2',
                                                       max_samples=0.7,
                                                       min_samples_leaf=3,
                                                       random_state=1)),
                               ('Gradient Boosting',
                                GradientBoostingClassifier(init=AdaBoostClassifier(random_state=1),
                                                           max_features=0.9,
                                                           n_estimators=200,
                                                           random_state=1,
                                                           subsample=1)),
                               ('AdaBoost',
                                AdaBoostClassifier(random_state=1))],
                   final_estimator=XGBClassifier(eval_metric='logloss',
                                                 random_state=1))


# Display the confusion matrix for the stacking model on the training data.

confusion_matrix_sklearn(stacking_classifier,X_train,y_train)


# Display the DataFrame of performance measures for the stacking model on the training data.

stacking_classifier_model_train_perf=model_performance_classification_sklearn(stacking_classifier,X_train,y_train)
print("Training performance:\n",stacking_classifier_model_train_perf)

Training performance:
    Accuracy  Recall  Precision    F1
0     0.788   0.900      0.806 0.850


# Display the confusion matrix for the stacking model on the test data.

confusion_matrix_sklearn(stacking_classifier,X_test,y_test)


# Display the DataFrame of performance measures for the stacking model on the test data.

stacking_classifier_model_test_perf=model_performance_classification_sklearn(stacking_classifier,X_test,y_test)
print("Testing performance:\n",stacking_classifier_model_test_perf)

Testing performance:
    Accuracy  Recall  Precision    F1
0     0.742   0.870      0.772 0.818


# Compare the performance of all models on the training data.

models_train_comp_df = pd.concat(
    [dtree_model_train_perf.T,dtree_estimator_model_train_perf.T,rf_model_train_perf.T,rf_estimator_model_train_perf.T,
     bagging_model_train_perf.T,bagging_estimator_model_train_perf.T,ab_classifier_model_train_perf.T,
     abc_tuned_model_train_perf.T,gb_classifier_model_train_perf.T,gbc_tuned_model_train_perf.T,stacking_classifier_model_train_perf.T],
    axis=1,
)
models_train_comp_df.columns = [
    "Decision Tree",
    "Decision Tree Estimator",
    "Random Forest",
    "Random Forest Tuned",
    "Bagging Classifier",
    "Bagging Estimator Tuned",
    "Adaboost Classifier",
    "Adaboost Classifier Tuned",
    "Gradient Boost Classifier",
    "Gradient Boost Classifier Tuned",
    "Stacking Classifier"]
print("Training performance comparison:")
models_train_comp_df

Training performance comparison:


# Compare the performance of all models on the test data.

models_test_comp_df = pd.concat(
    [dtree_model_test_perf.T,dtree_estimator_model_test_perf.T,rf_model_test_perf.T,rf_estimator_model_test_perf.T,
     bagging_model_test_perf.T,bagging_estimator_model_test_perf.T,ab_classifier_model_test_perf.T,
     abc_tuned_model_test_perf.T,gb_classifier_model_test_perf.T,gbc_tuned_model_test_perf.T,stacking_classifier_model_test_perf.T],
    axis=1,
)
models_test_comp_df.columns = [
    "Decision Tree",
    "Decision Tree Estimator",
    "Random Forest",
    "Random Forest Tuned",
    "Bagging Classifier",
    "Bagging Estimator Tuned",
    "Adaboost Classifier",
    "Adaboost Classifier Tuned",
    "Gradient Boost Classifier",
    "Gradient Boost Classifier Tuned",
    "Stacking Classifier"]
print("Test performance comparison:")
models_test_comp_df

Test performance comparison:


# Visualize the feature importance for the final model.

feature_names = X_train.columns
importances = gbc_tuned.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(12,12))
plt.title('Feature Importances')
plt.barh(range(len(indices)), importances[indices], color='violet', align='center')
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel('Relative Importance')
plt.show()


# Import libraries for data manipulation.
import pandas as pd
import numpy as np

# Import libraries for data visualization.
import matplotlib.pyplot as plt
import seaborn as sns

# Import library to split data.
from sklearn.model_selection import train_test_split

# Impute SimpleImputer to deal with missing values.
from sklearn.impute import SimpleImputer

# Import functions to evaluate model performance.
from sklearn import metrics
from sklearn.metrics import confusion_matrix, classification_report
from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score

# Import library to build a logistic regression model.
from sklearn.linear_model import LogisticRegression

# Import library to build a decision tree model.
from sklearn.tree import DecisionTreeClassifier

# Import ensemble methods.
from sklearn.ensemble import BaggingClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier

# Import libraries for k-fold cross validation.
from sklearn.model_selection import StratifiedKFold, cross_val_score

# Import libraries to oversample and undersample data.
from imblearn.over_sampling import SMOTE
from imblearn.under_sampling import RandomUnderSampler

# Import RandomizedSearchCV for model tuning.
from sklearn.model_selection import RandomizedSearchCV

# Import libraries to create and modify pipelines.
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer

# Import libraries to ignore irrelevant warnings.
import warnings
warnings.filterwarnings('ignore')


# Set the precision of floating numbers to 3 decimal points.
pd.set_option("display.float_format", lambda x: "%.3f" % x)


# Mount Google Drive.

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive


# Load the data sets.

train = pd.read_csv('/content/drive/My Drive/Data science/Data sets/Train.csv')
test = pd.read_csv('/content/drive/My Drive/Data science/Data sets/Test.csv')


# Create copies of the data sets to avoid altering the original data.

train0 = train.copy()
test0 = test.copy()


# Use print function and .shape attribute to display the number of rows & columns in each data set.

print('There are',train0.shape[0],'rows and',train0.shape[1],'columns in the training data set.')
print('There are',test0.shape[0],'rows and',test0.shape[1],'columns in the testing data set.')

There are 40000 rows and 41 columns in the training data set.
There are 10000 rows and 41 columns in the testing data set.


# Display a sample of 5 rows from each data set to get a general idea of the information & make sure they are loaded properly.

train0.sample(5)


test0.sample(5)


# Use .info() method to check the non-null counts and data types of each column in the training set.

train0.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 40000 entries, 0 to 39999
Data columns (total 41 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   V1      39954 non-null  float64
 1   V2      39961 non-null  float64
 2   V3      40000 non-null  float64
 3   V4      40000 non-null  float64
 4   V5      40000 non-null  float64
 5   V6      40000 non-null  float64
 6   V7      40000 non-null  float64
 7   V8      40000 non-null  float64
 8   V9      40000 non-null  float64
 9   V10     40000 non-null  float64
 10  V11     40000 non-null  float64
 11  V12     40000 non-null  float64
 12  V13     40000 non-null  float64
 13  V14     40000 non-null  float64
 14  V15     40000 non-null  float64
 15  V16     40000 non-null  float64
 16  V17     40000 non-null  float64
 17  V18     40000 non-null  float64
 18  V19     40000 non-null  float64
 19  V20     40000 non-null  float64
 20  V21     40000 non-null  float64
 21  V22     40000 non-null  float64
 22  V23     40000 non-null  float64
 23  V24     40000 non-null  float64
 24  V25     40000 non-null  float64
 25  V26     40000 non-null  float64
 26  V27     40000 non-null  float64
 27  V28     40000 non-null  float64
 28  V29     40000 non-null  float64
 29  V30     40000 non-null  float64
 30  V31     40000 non-null  float64
 31  V32     40000 non-null  float64
 32  V33     40000 non-null  float64
 33  V34     40000 non-null  float64
 34  V35     40000 non-null  float64
 35  V36     40000 non-null  float64
 36  V37     40000 non-null  float64
 37  V38     40000 non-null  float64
 38  V39     40000 non-null  float64
 39  V40     40000 non-null  float64
 40  Target  40000 non-null  int64  
dtypes: float64(40), int64(1)
memory usage: 12.5 MB


# Use .info() method to check the non-null counts and data types of each column in the test set.

test0.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 41 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   V1      9989 non-null   float64
 1   V2      9993 non-null   float64
 2   V3      10000 non-null  float64
 3   V4      10000 non-null  float64
 4   V5      10000 non-null  float64
 5   V6      10000 non-null  float64
 6   V7      10000 non-null  float64
 7   V8      10000 non-null  float64
 8   V9      10000 non-null  float64
 9   V10     10000 non-null  float64
 10  V11     10000 non-null  float64
 11  V12     10000 non-null  float64
 12  V13     10000 non-null  float64
 13  V14     10000 non-null  float64
 14  V15     10000 non-null  float64
 15  V16     10000 non-null  float64
 16  V17     10000 non-null  float64
 17  V18     10000 non-null  float64
 18  V19     10000 non-null  float64
 19  V20     10000 non-null  float64
 20  V21     10000 non-null  float64
 21  V22     10000 non-null  float64
 22  V23     10000 non-null  float64
 23  V24     10000 non-null  float64
 24  V25     10000 non-null  float64
 25  V26     10000 non-null  float64
 26  V27     10000 non-null  float64
 27  V28     10000 non-null  float64
 28  V29     10000 non-null  float64
 29  V30     10000 non-null  float64
 30  V31     10000 non-null  float64
 31  V32     10000 non-null  float64
 32  V33     10000 non-null  float64
 33  V34     10000 non-null  float64
 34  V35     10000 non-null  float64
 35  V36     10000 non-null  float64
 36  V37     10000 non-null  float64
 37  V38     10000 non-null  float64
 38  V39     10000 non-null  float64
 39  V40     10000 non-null  float64
 40  Target  10000 non-null  int64  
dtypes: float64(40), int64(1)
memory usage: 3.1 MB


# Check the statistical summary for the training data set.

train0.describe()


# Check the statistical summary for the testing data set.

test0.describe()


# Check for duplicated values in the training and testing data sets.

print('There are',train0.duplicated().sum(),'duplicated values in the training set.')
print('There are',test0.duplicated().sum(),'duplicated values in the test set.')

There are 0 duplicated values in the training set.
There are 0 duplicated values in the test set.


# Check for missing (null) values in the training data set.

train0.isnull().sum()[train0.isnull().sum()>0]

V1    46
V2    39
dtype: int64


# Check for missing (null) values in the testing data set.

test0.isnull().sum()[test0.isnull().sum()>0]

V1    11
V2     7
dtype: int64


# Define a function to plot a boxplot and a histogram along the same scale.

def histogram_boxplot(data, feature, figsize=(12, 7), kde=False, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (12,7))
    kde: whether to the show density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows=2,  # Number of rows of the subplot grid= 2
        sharex=True,  # x-axis will be shared among all subplots
        gridspec_kw={"height_ratios": (0.25, 0.75)},
        figsize=figsize,
    )  # creating the 2 subplots
    sns.boxplot(
        data=data, x=feature, ax=ax_box2, showmeans=True, color="skyblue"
    )  # boxplot will be created and a star will indicate the mean value of the column
    sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2, bins=bins, palette="winter"
    ) if bins else sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2
    )  # For histogram
    ax_hist2.axvline(
        data[feature].mean(), color="green", linestyle="--"
    )  # Add mean to the histogram
    ax_hist2.axvline(
        data[feature].median(), color="black", linestyle="-"
    )  # Add median to the histogram


sns.set_palette("Set3")


# Plot histograms and boxplots for each of the features in the training data set.

for feature in train0.drop('Target', axis=1).columns:
    histogram_boxplot(train0, feature, figsize=(12, 7), kde=False, bins=None)


# Plot histograms and boxplots for each of the features in the testing data set.

for feature in test0.drop('Target', axis=1).columns:
    histogram_boxplot(test0, feature, figsize=(12, 7), kde=False, bins=None)


# Visualize the distribution of the target variable in the training data set using countplot.

sns.set_palette("Pastel1")
plt.title('Countplot: Generator Failure (training data)')
sns.countplot(data=train0, x ='Target')
plt.xlabel("Generator Failure")
plt.ylabel('Count');


# Print the percentage of each value for the target variable in the training set.

print("Percentage of classes in training set:")
print(train0.Target.value_counts(normalize=True))

Percentage of classes in training set:
0   0.945
1   0.055
Name: Target, dtype: float64


# Visualize the distribution of the target variable in the testing data set using countplot.

plt.title('Countplot: Generator Failure (test data)')
sns.countplot(data=test0, x ='Target')
plt.xlabel("Generator Failure")
plt.ylabel('Count');


# Print the percentage of each value for the target variable in the test set.

print("Percentage of classes in test set:")
print(test0.Target.value_counts(normalize=True))

Percentage of classes in test set:
0   0.945
1   0.055
Name: Target, dtype: float64


# Separate the x & y variables in the training data set.
X_train0 = train0.drop(['Target'],axis=1)
y_train0 = train0['Target']

# Separate the x & y variables in the test data set.
X_test = test0.drop(['Target'], axis=1)
y_test = test0['Target']


# Split the training data set into a new training set and validation set.

X_train, X_val, y_train, y_val = train_test_split(X_train0, y_train0, test_size=0.3, random_state=1, stratify=y_train0)


# Print the shapes of the new training set, the validation set and the test set to verify that they have been distributed appropriately.

print(X_train.shape, X_val.shape, X_test.shape)

(28000, 40) (12000, 40) (10000, 40)


# Define the imputer to replace null values with the median value for that feature.
imp_median = SimpleImputer(missing_values=np.nan, strategy="median")

# Fit the imputer on the training data columns with null values and transform the training data.
X_train["V1"], X_train["V2"] = imp_median.fit_transform(X_train[["V1"]]), imp_median.fit_transform(X_train[["V2"]])

# Transform the validation and test data using the imputer fit on the training data.
X_val["V1"], X_val["V2"] = imp_median.transform(X_val[["V1"]]), imp_median.transform(X_val[["V2"]])
X_test["V1"], X_test["V2"] = imp_median.transform(X_test[["V1"]]), imp_median.transform(X_test[["V2"]])


# Verify that there are no missing values remaining in the training, validation and test sets.

print(X_train.isnull().sum()[X_train.isnull().sum()>0])
print(X_val.isnull().sum()[X_train.isnull().sum()>0])
print(X_test.isnull().sum()[X_train.isnull().sum()>0])

Series([], dtype: int64)
Series([], dtype: int64)
Series([], dtype: int64)


# Define a function to compute different metrics to check performance of a classification model built using sklearn.

def model_performance_classification_sklearn(model, predictors, target):
    """
    Function to compute different metrics to check classification model performance

    model: classifier
    predictors: independent variables
    target: dependent variable
    """

    # predicting using the independent variables
    pred = model.predict(predictors)

    acc = accuracy_score(target, pred)  # to compute accuracy
    recall = recall_score(target, pred)  # to compute recall
    precision = precision_score(target, pred)  # to compute precision
    f1 = f1_score(target, pred)  # to compute F1-score

    # creating a DataFrame of metrics
    df_perf = pd.DataFrame(
        {
            "Accuracy": acc,
            "Recall": recall,
            "Precision": precision,
            "F1": f1
            
        },
        index=[0],
    )

    return df_perf


# Create a user-defined function to display a confusion matrix for classification models.

def confusion_matrix_sklearn(model, predictors, target):
    """
    To plot the confusion_matrix with percentages

    model: classifier
    predictors: independent variables
    target: dependent variable
    """
    y_pred = model.predict(predictors)
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ["{0:0.0f}".format(item) + "\n{0:.2%}".format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")
    plt.ylabel("True label")
    plt.xlabel("Predicted label")


# Define a scorer to compare parameter combinations.

scorer = metrics.make_scorer(metrics.recall_score)


# Create an empty list to store all the models.
models = []

# Appending 6 models into the list
models.append(("Decision tree", DecisionTreeClassifier(random_state=1)))
models.append(("Logistic regression", LogisticRegression(random_state=1)))
models.append(("Random forest", DecisionTreeClassifier(random_state=1)))
models.append(("Bagging", BaggingClassifier(random_state=1)))
models.append(("AdaBoost", AdaBoostClassifier(random_state=1)))
models.append(("Gradient boost", GradientBoostingClassifier(random_state=1)))

# Create an empty list to store all model's CV scores.
results1 = []

# Create an empty list to store the model names.
names = []  

# Loop through all the models to get the mean cross validated score.
print("\n" "Cross-Validation Cost:" "\n")

for name, model in models:
    kfold = StratifiedKFold(
        n_splits=5, shuffle=True, random_state=1
    )  # Setting number of splits equal to 5
    cv_result = cross_val_score(
        estimator=model, X=X_train, y=y_train, scoring=scorer, cv=kfold
    )
    results1.append(cv_result)
    names.append(name)
    print("{}: {}".format(name, cv_result.mean()))

print("\n" "Validation Performance:" "\n")

for name, model in models:
    model.fit(X_train, y_train)
    scores = recall_score(y_val, model.predict(X_val))
    print("{}: {}".format(name, scores))

Cross-Validation Cost:

Decision tree: 0.7413212407655788
Logistic regression: 0.48792872197739035
Random forest: 0.7413212407655788
Bagging: 0.7256583849609334
AdaBoost: 0.6192012092567755
Gradient boost: 0.7230291030635925

Validation Performance:

Decision tree: 0.7454268292682927
Logistic regression: 0.4634146341463415
Random forest: 0.7454268292682927
Bagging: 0.7240853658536586
AdaBoost: 0.6051829268292683
Gradient boost: 0.7195121951219512


# Create a DataFrame to store the cross validation scores for each model.

cv_scores = pd.DataFrame(results1, columns=[1,2,3,4,5], index=names)
cv_scores.T


# Use a for loop to display boxplots for each of the models' cross validation scores.

plt.figure(figsize=(15,3))

for i, model in enumerate(names):
    plt.subplot(1, 6, i+1)
    plt.boxplot(cv_scores.T[model], whis=1.5)
    plt.tight_layout()
    plt.title(model)

plt.show()


# Use the Synthetic Minority Over Sampling Technique (SMOTE) to increase the importance of the minority class and thereby improve recall.

sm = SMOTE(sampling_strategy=1, k_neighbors=5, random_state=1)
X_train_over, y_train_over = sm.fit_resample(X_train, y_train)


# Print label counts before and after oversampling to verify that the technique has been correctly executed.

print("Before Oversampling, counts of label 'Yes': {}".format(sum(y_train == 1)))
print("Before Oversampling, counts of label 'No': {} \n".format(sum(y_train == 0)))

print("After Oversampling, counts of label 'Yes': {}".format(sum(y_train_over == 1)))
print("After Oversampling, counts of label 'No': {} \n".format(sum(y_train_over == 0)))

print("After Oversampling, the shape of train_X: {}".format(X_train_over.shape))
print("After Oversampling, the shape of train_y: {} \n".format(y_train_over.shape))

Before Oversampling, counts of label 'Yes': 1531
Before Oversampling, counts of label 'No': 26469 

After Oversampling, counts of label 'Yes': 26469
After Oversampling, counts of label 'No': 26469 

After Oversampling, the shape of train_X: (52938, 40)
After Oversampling, the shape of train_y: (52938,)


# Create an empty list to store all model's CV scores.
results_over = []

# Loop through all the models to get the mean cross validated score.
print("\n" "Cross-Validation Cost:" "\n")

for name, model in models:
    kfold = StratifiedKFold(
        n_splits=5, shuffle=True, random_state=1
    )  # Setting number of splits equal to 5
    cv_result_over = cross_val_score(
        estimator=model, X=X_train_over, y=y_train_over, scoring=scorer, cv=kfold
    )
    results_over.append(cv_result_over)
    print("{}: {}".format(name, cv_result_over.mean()))

print("\n" "Validation Performance:" "\n")

for name, model in models:
    model.fit(X_train_over, y_train_over)
    scores_over = recall_score(y_val, model.predict(X_val))
    print("{}: {}".format(name, scores_over))

Cross-Validation Cost:

Decision tree: 0.9689069274906782
Logistic regression: 0.8747214299831179
Random forest: 0.9689069274906782
Bagging: 0.9747252485284147
AdaBoost: 0.8942159673577901
Gradient boost: 0.9163928365232223

Validation Performance:

Decision tree: 0.8125
Logistic regression: 0.8399390243902439
Random forest: 0.8125
Bagging: 0.8414634146341463
AdaBoost: 0.8536585365853658
Gradient boost: 0.8765243902439024


# Create a DataFrame to store the cross validation scores for each model built on the oversampled data.

cv_scores_over = pd.DataFrame(results_over, columns=[1,2,3,4,5], index=names)
cv_scores_over.T


# Use a for loop to display boxplots for each of the models' cross validation scores on the oversampled data.

plt.figure(figsize=(15,3))

for i, model in enumerate(names):
    plt.subplot(1, 6, i+1)
    plt.boxplot(cv_scores_over.T[model], whis=1.5)
    plt.tight_layout()
    plt.title(model)

plt.show()


# Use the RandomUnderSampler technique to reduce the importance of the majority class and thereby improve recall.

rus = RandomUnderSampler(random_state=1, sampling_strategy=1)
X_train_un, y_train_un = rus.fit_resample(X_train, y_train)


# Print label counts before and after undersampling to verify that the technique has been correctly executed.

print("Before Under Sampling, counts of label 'Yes': {}".format(sum(y_train == 1)))
print("Before Under Sampling, counts of label 'No': {} \n".format(sum(y_train == 0)))

print("After Under Sampling, counts of label 'Yes': {}".format(sum(y_train_un == 1)))
print("After Under Sampling, counts of label 'No': {} \n".format(sum(y_train_un == 0)))

print("After Under Sampling, the shape of train_X: {}".format(X_train_un.shape))
print("After Under Sampling, the shape of train_y: {} \n".format(y_train_un.shape))

Before Under Sampling, counts of label 'Yes': 1531
Before Under Sampling, counts of label 'No': 26469 

After Under Sampling, counts of label 'Yes': 1531
After Under Sampling, counts of label 'No': 1531 

After Under Sampling, the shape of train_X: (3062, 40)
After Under Sampling, the shape of train_y: (3062,)


# Create an empty list to store all model's CV scores.
results_un = []

# Loop through all the models to get the mean cross validated score.
print("\n" "Cross-Validation Cost:" "\n")

for name, model in models:
    kfold = StratifiedKFold(
        n_splits=5, shuffle=True, random_state=1
    )  # Setting number of splits equal to 5
    cv_result_un = cross_val_score(
        estimator=model, X=X_train_un, y=y_train_un, scoring=scorer, cv=kfold
    )
    results_un.append(cv_result_un)
    print("{}: {}".format(name, cv_result_un.mean()))

print("\n" "Validation Performance:" "\n")

for name, model in models:
    model.fit(X_train_un, y_train_un)
    scores_un = recall_score(y_val, model.predict(X_val))
    print("{}: {}".format(name, scores_un))

Cross-Validation Cost:

Decision tree: 0.8510804538970854
Logistic regression: 0.8517063720167763
Random forest: 0.8510804538970854
Bagging: 0.8706691362755743
AdaBoost: 0.8602243937748824
Gradient boost: 0.8850354474037172

Validation Performance:

Decision tree: 0.8384146341463414
Logistic regression: 0.836890243902439
Random forest: 0.8384146341463414
Bagging: 0.8673780487804879
AdaBoost: 0.8628048780487805
Gradient boost: 0.8765243902439024


# Create a DataFrame to store the cross validation scores for each model built on the undersampled data.

cv_scores_un = pd.DataFrame(results_un, columns=[1,2,3,4,5], index=names)
cv_scores_un.T


# Use a for loop to display boxplots for each of the models' cross validation scores on the oversampled data.

plt.figure(figsize=(15,3))

for i, model in enumerate(names):
    plt.subplot(1, 6, i+1)
    plt.boxplot(cv_scores_un.T[model], whis=1.5)
    plt.tight_layout()
    plt.title(model)

plt.show()


# Define the model
Model = BaggingClassifier(random_state=1)

# Parameter grid to pass in RandomSearchCV
param_grid = {'max_samples': [0.8,0.9,1], 'max_features': [0.7,0.8,0.9], 'n_estimators' : [30,50,70]}

# Calling RandomizedSearchCV
randomized_cv = RandomizedSearchCV(estimator=Model, param_distributions=param_grid, n_iter=10, n_jobs = -1, scoring=scorer, cv=5, random_state=1)

# Fitting parameters in RandomizedSearchCV
randomized_cv.fit(X_train_un,y_train_un)

print("Best parameters are {} with CV score={}:" .format(randomized_cv.best_params_,randomized_cv.best_score_))

Best parameters are {'n_estimators': 70, 'max_samples': 1, 'max_features': 0.8} with CV score=1.0:


# Build a bagging model with the best parameters

bag_tuned = BaggingClassifier(
    n_estimators=70,
    max_samples=1,
    max_features=0.8,
    random_state=1)

# Fit the model on undersampled training data
bag_tuned.fit(X_train_un, y_train_un)

BaggingClassifier(max_features=0.8, max_samples=1, n_estimators=70,
                  random_state=1)


# Calculate performance of the tuned model on the training data

bag_tuned_perf_train = model_performance_classification_sklearn(bag_tuned, X_train, y_train)
print("Training performance:")
bag_tuned_perf_train

Training performance:


# Calculate performance metrics on the validation set

bag_tuned_perf_val = model_performance_classification_sklearn(bag_tuned, X_val, y_val)
print("Validation performance:")
bag_tuned_perf_val

Validation performance:


# Display the confusion matrix for the tuned model on the validation set

confusion_matrix_sklearn(bag_tuned, X_val, y_val)


# Define the model
Model2 = AdaBoostClassifier(random_state=1)

# Parameter grid to pass in RandomSearchCV
param_grid2 = { "n_estimators": [100, 150, 200], 
                "learning_rate": [0.2, 0.05], 
                "base_estimator": [DecisionTreeClassifier(max_depth=1, random_state=1), 
                                   DecisionTreeClassifier(max_depth=2, random_state=1), 
                                   DecisionTreeClassifier(max_depth=3, random_state=1)]}

# Calling RandomizedSearchCV
randomized_cv2 = RandomizedSearchCV(estimator=Model2, param_distributions=param_grid2, n_iter=10, n_jobs=-1, scoring=scorer, cv=5, random_state=1)

#Fitting parameters in RandomizedSearchCV
randomized_cv2.fit(X_train_un,y_train_un)

print("Best parameters are {} with CV score={}:" .format(randomized_cv2.best_params_, randomized_cv2.best_score_))

Best parameters are {'n_estimators': 200, 'learning_rate': 0.2, 'base_estimator': DecisionTreeClassifier(max_depth=3, random_state=1)} with CV score=0.8883076792063187:


# Build an AdaBoost model with the best parameters

ada_tuned = AdaBoostClassifier(
    n_estimators=200,
    learning_rate=0.2,
    random_state=1,
    base_estimator=DecisionTreeClassifier(max_depth=3, random_state=1))

# Fit the model on undersampled training data
ada_tuned.fit(X_train_un, y_train_un)

AdaBoostClassifier(base_estimator=DecisionTreeClassifier(max_depth=3,
                                                         random_state=1),
                   learning_rate=0.2, n_estimators=200, random_state=1)


# Calculate performance of the tuned model on the training data

ada_tuned_perf_train = model_performance_classification_sklearn(ada_tuned, X_train, y_train)
print("Training performance:")
ada_tuned_perf_train

Training performance:


# Calculate performance metrics on the validation set

ada_tuned_perf_val = model_performance_classification_sklearn(ada_tuned, X_val, y_val)
print("Validation performance:")
ada_tuned_perf_val

Validation performance:


# Display the confusion matrix for the tuned model on the validation set

confusion_matrix_sklearn(ada_tuned, X_val, y_val)


# Define the model
Model3 = GradientBoostingClassifier(random_state=1)

# Parameter grid to pass in RandomSearchCV
param_grid3 = {"n_estimators": np.arange(100,150,25), "learning_rate": [0.2, 0.05, 1], "subsample":[0.5,0.7], "max_features":[0.5,0.7]}

# Calling RandomizedSearchCV
randomized_cv3 = RandomizedSearchCV(estimator=Model3, param_distributions=param_grid3, n_iter=10, n_jobs = -1, scoring=scorer, cv=5, random_state=1)

#Fitting parameters in RandomizedSearchCV
randomized_cv3.fit(X_train_un,y_train_un)

print("Best parameters are {} with CV score={}:" .format(randomized_cv3.best_params_, randomized_cv3.best_score_))

Best parameters are {'subsample': 0.5, 'n_estimators': 100, 'max_features': 0.7, 'learning_rate': 0.2} with CV score=0.8955036086095675:


# Build a gradient boost model with the best parameters

gboost_tuned = GradientBoostingClassifier(
    subsample=0.5,
    n_estimators=100,
    max_features=0.7,
    learning_rate=0.2,
    random_state=1)

# Fit the model on undersampled training data
gboost_tuned.fit(X_train_un, y_train_un)

GradientBoostingClassifier(learning_rate=0.2, max_features=0.7, random_state=1,
                           subsample=0.5)


# Calculate performance of the tuned model on the training data

gboost_tuned_perf_train = model_performance_classification_sklearn(gboost_tuned, X_train, y_train)
print("Training performance:")
gboost_tuned_perf_train

Training performance:


# Calculate performance metrics on the validation set

gboost_tuned_perf_val = model_performance_classification_sklearn(gboost_tuned, X_val, y_val)
print("Validation performance:")
gboost_tuned_perf_val

Validation performance:


# Display the confusion matrix for the tuned model on the validation set

confusion_matrix_sklearn(gboost_tuned, X_val, y_val)


# Build a DataFrame to compare the performance measures for the 3 tuned models on the training data.

models_train_comp_df = pd.concat(
    [
        bag_tuned_perf_train.T,
        ada_tuned_perf_train.T,
        gboost_tuned_perf_train.T
    ],
    axis=1,
)
models_train_comp_df.columns = [
    "Tuned bagging model",
    "Tuned AdaBoost model",
    "Tuned gradient boost model",
]
print("Training performance comparison:")
models_train_comp_df

Training performance comparison:


# Build a DataFrame to compare the performance measures for the 3 tuned models on the validation data.

models_val_comp_df = pd.concat(
    [
        bag_tuned_perf_val.T,
        ada_tuned_perf_val.T,
        gboost_tuned_perf_val.T
    ],
    axis=1,
)
models_val_comp_df.columns = [
    "Tuned bagging model",
    "Tuned AdaBoost model",
    "Tuned gradient boost model",
]
print("Validation performance comparison:")
models_val_comp_df

Validation performance comparison:


# Calculate the final model's performance on the test set.

ada_tuned_perf_test = model_performance_classification_sklearn(ada_tuned, X_test, y_test)
print("Test performance:")
ada_tuned_perf_test

Test performance:


# Visualize importance of the features in the final model.

feature_names = X_train.columns
importances = ada_tuned.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(12, 12))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()


# Separate the variables to re-build the final model with a pipeline.
X_pipe = train0.drop(['Target'], axis=1)
Y_pipe = train0['Target']

# Separate the x & y variables in the test data set.
X_test_pipe = test0.drop(['Target'], axis=1)
y_test_pipe = test0['Target']


# Impute the missing values in the training and testing sets.

imputer = SimpleImputer(strategy="median")
X_pipe2 = imputer.fit_transform(X_pipe)
X_test_pipe2 = imputer.fit_transform(X_test_pipe)


# Apply the undersampling technique on the training data.

rus2 = RandomUnderSampler(random_state=1, sampling_strategy=1)
X_pipe_un, y_pipe_un = rus2.fit_resample(X_pipe2, Y_pipe)


# Create the pipeline for the tuned AdaBoost model.
Model = Pipeline(steps=[("Ada", AdaBoostClassifier(
    n_estimators=200,
    learning_rate=0.2,
    random_state=1,
    base_estimator=DecisionTreeClassifier(max_depth=3, random_state=1)))])

# Fit the model on the undersampled training data.
Model.fit(X_pipe_un, y_pipe_un)

Pipeline(steps=[('Ada',
                 AdaBoostClassifier(base_estimator=DecisionTreeClassifier(max_depth=3,
                                                                          random_state=1),
                                    learning_rate=0.2, n_estimators=200,
                                    random_state=1))])


# Check the model's performance on the test data.

Model_test = model_performance_classification_sklearn(Model, X_test_pipe2, y_test_pipe)
Model_test


# Import libraries for data manipulation.
import pandas as pd
import numpy as np

# Import libraries for data visualization.
import matplotlib.pyplot as plt
import seaborn as sns

# Import library for scaling data.
from sklearn.preprocessing import StandardScaler

# Import library to build K-means clustering model.
from sklearn.cluster import KMeans

# Import library to compute distances.
from scipy.spatial.distance import cdist

# Import library to compute silhouette scores.
from sklearn.metrics import silhouette_score

# Import library to visualize silhouette scores.
from yellowbrick.cluster import SilhouetteVisualizer

# Import linkage methods & cophenetic correlation for hierarchical clustering.
from scipy.cluster.hierarchy import linkage, cophenet

# Import library to compute pairwise distance.
from scipy.spatial.distance import pdist

# Import dendrogram to visualize hierarchical clustering.
from scipy.cluster.hierarchy import dendrogram

# Import library to build a hierarchical clustering model.
from sklearn.cluster import AgglomerativeClustering


# Set the precision of floating numbers to 3 decimal points.
pd.set_option("display.float_format", lambda x: "%.3f" % x)


# Mount Google Drive.

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive


# Load the data set.

df = pd.read_csv('/content/drive/My Drive/Data science/Data sets/stock_data.csv')


# Create a copy of the data set to avoid altering the original data.

data = df.copy()


# Use print function and .shape attribute to display the number of rows & columns in the data set.

print('There are',data.shape[0],'rows and',data.shape[1],'columns in the data set.')

There are 340 rows and 15 columns in the data set.


# Display a sample of 10 rows from the data set to get a general idea of the information & make sure it is loaded properly.

data.sample(10)


# Use .info() method to check the non-null counts and data types of each column in the data set.

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 340 entries, 0 to 339
Data columns (total 15 columns):
 #   Column                        Non-Null Count  Dtype  
---  ------                        --------------  -----  
 0   Ticker Symbol                 340 non-null    object 
 1   Security                      340 non-null    object 
 2   GICS Sector                   340 non-null    object 
 3   GICS Sub Industry             340 non-null    object 
 4   Current Price                 340 non-null    float64
 5   Price Change                  340 non-null    float64
 6   Volatility                    340 non-null    float64
 7   ROE                           340 non-null    int64  
 8   Cash Ratio                    340 non-null    int64  
 9   Net Cash Flow                 340 non-null    int64  
 10  Net Income                    340 non-null    int64  
 11  Earnings Per Share            340 non-null    float64
 12  Estimated Shares Outstanding  340 non-null    float64
 13  P/E Ratio                     340 non-null    float64
 14  P/B Ratio                     340 non-null    float64
dtypes: float64(7), int64(4), object(4)
memory usage: 40.0+ KB


# Check the statistical summary for the data set.

data.describe().T


# Check for duplicated values in the data set.

print('There are',data.duplicated().sum(),'duplicated values in the data set.')

There are 0 duplicated values in the data set.


# Check for missing (null) values in the data set.

data.isnull().sum()

Ticker Symbol                   0
Security                        0
GICS Sector                     0
GICS Sub Industry               0
Current Price                   0
Price Change                    0
Volatility                      0
ROE                             0
Cash Ratio                      0
Net Cash Flow                   0
Net Income                      0
Earnings Per Share              0
Estimated Shares Outstanding    0
P/E Ratio                       0
P/B Ratio                       0
dtype: int64


# Create a user-defined function to display histogram & boxplot together for numeric variables.

def histogram_boxplot(data, feature, figsize=(18, 5), kde=True, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (18,5))
    kde: whether to show the density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows=2,  # Number of rows of the subplot grid= 2
        sharex=True,  # x-axis will be shared among all subplots
        gridspec_kw={"height_ratios": (0.3, 0.7)},
        figsize=figsize,
    )  # creating the 2 subplots
    sns.boxplot(
        data=data, x=feature, ax=ax_box2, showmeans=True, color="skyblue"
    )  # boxplot will be created and a triangle will indicate the mean value of the column
    sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2, bins=bins, palette="winter"
    ) if bins else sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2
    )  # For histogram
    ax_hist2.axvline(
        data[feature].mean(), color="green", linestyle="--"
    )  # Add mean to the histogram
    ax_hist2.axvline(
        data[feature].median(), color="black", linestyle="-"
    )  # Add median to the histogram


# Visualize histogram & boxplot for stock prices.

sns.set_palette("Set3")
histogram_boxplot(data=data, feature='Current Price')


# Display the statistical summary for current stock price.

data.describe().T.loc['Current Price']

count    340.000
mean      80.862
std       98.055
min        4.500
25%       38.555
50%       59.705
75%       92.880
max     1274.950
Name: Current Price, dtype: float64


# Use a barplot to visualize the average price increase across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='Price Change', 
            order=data.groupby(['GICS Sector'])['Price Change'].mean().reset_index().sort_values('Price Change')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average price change for each sector.

data.groupby(['GICS Sector'])['Price Change'].mean().sort_values(ascending=False)

GICS Sector
Health Care                     9.586
Consumer Staples                8.685
Information Technology          7.217
Telecommunications Services     6.957
Real Estate                     6.206
Consumer Discretionary          5.846
Materials                       5.590
Financials                      3.865
Industrials                     2.833
Utilities                       0.804
Energy                        -10.228
Name: Price Change, dtype: float64


# Use heatmap to visualize correlation between numeric variables.

plt.figure(figsize=(15, 8))
sns.heatmap(data.corr(), annot=True);


# Use a for loop with logical indexing to create a DataFrame displaying the attributes with correlation above 0.3.

corr = pd.DataFrame()

for row in data.corr().index:
  corr = pd.concat([corr, data.corr()[row][abs(data.corr()[row])>0.3].drop(row)], axis=1)

corr.dropna(axis=1,how='all')


# Use a barplot to visualize the average cash ratio across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='Cash Ratio', 
            order=data.groupby(['GICS Sector'])['Cash Ratio'].mean().reset_index().sort_values('Cash Ratio')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average cash ratio for each sector.

data.groupby(['GICS Sector'])['Cash Ratio'].mean().sort_values(ascending=False)

GICS Sector
Information Technology        149.818
Telecommunications Services   117.000
Health Care                   103.775
Financials                     98.592
Consumer Staples               70.947
Energy                         51.133
Real Estate                    50.111
Consumer Discretionary         49.575
Materials                      41.700
Industrials                    36.189
Utilities                      13.625
Name: Cash Ratio, dtype: float64


# Use a barplot to visualize the average P/E ratio across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='P/E Ratio', 
            order=data.groupby(['GICS Sector'])['P/E Ratio'].mean().reset_index().sort_values('P/E Ratio')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average P/E ratio for each sector.

data.groupby(['GICS Sector'])['P/E Ratio'].mean().sort_values(ascending=False)

GICS Sector
Energy                        72.898
Information Technology        43.783
Real Estate                   43.066
Health Care                   41.135
Consumer Discretionary        35.212
Consumer Staples              25.521
Materials                     24.585
Utilities                     18.719
Industrials                   18.259
Financials                    16.023
Telecommunications Services   12.223
Name: P/E Ratio, dtype: float64


# Visualize the distribution of GICS Sector using countplot.

plt.figure(figsize=(18, 5))
plt.title('Countplot: GICS Sector')
sns.countplot(data=data, x ='GICS Sector', order=data['GICS Sector'].value_counts().reset_index()['index'].tolist())
plt.ylabel('Count')
plt.xticks(rotation=20);


# Display the count of companies in each sector using .value_counts().

data['GICS Sector'].value_counts()

Industrials                    53
Financials                     49
Health Care                    40
Consumer Discretionary         40
Information Technology         33
Energy                         30
Real Estate                    27
Utilities                      24
Materials                      20
Consumer Staples               19
Telecommunications Services     5
Name: GICS Sector, dtype: int64


# Visualize the distribution of GICS Sub Industries using countplot.

plt.figure(figsize=(20, 5))
plt.title('Countplot: GICS Sub Industry')
sns.countplot(data=data, x ='GICS Sub Industry', order=data['GICS Sub Industry'].value_counts().reset_index()['index'].tolist())
plt.ylabel('Count')
plt.xticks(rotation=90);


# Display the most common sub-industries using value_counts().

data['GICS Sub Industry'].value_counts().head(8)

Oil & Gas Exploration & Production    16
REITs                                 14
Industrial Conglomerates              14
Electric Utilities                    12
Internet Software & Services          12
Health Care Equipment                 11
MultiUtilities                        11
Banks                                 10
Name: GICS Sub Industry, dtype: int64


# Visualize histogram & boxplot for price change.

sns.set_palette("Set3")
histogram_boxplot(data=data, feature='Price Change')


# Display the statistical summary for price change.

data.describe().T.loc['Price Change']

count   340.000
mean      4.078
std      12.006
min     -47.130
25%      -0.939
50%       4.820
75%      10.695
max      55.052
Name: Price Change, dtype: float64


# Visualize histogram & boxplot for volatility.

histogram_boxplot(data=data, feature='Volatility')


# Display the statistical summary for volatility.

data.describe().T.loc['Volatility']

count   340.000
mean      1.526
std       0.592
min       0.733
25%       1.135
50%       1.386
75%       1.696
max       4.580
Name: Volatility, dtype: float64


# Visualize histogram & boxplot for ROE.

histogram_boxplot(data=data, feature='ROE')


# Display the statistical summary for ROE.

data.describe().T.loc['ROE']

count   340.000
mean     39.597
std      96.548
min       1.000
25%       9.750
50%      15.000
75%      27.000
max     917.000
Name: ROE, dtype: float64


# Visualize histogram & boxplot for Cash Ratio.

histogram_boxplot(data=data, feature='Cash Ratio')


# Display the statistical summary for cash ratio.

data.describe().T.loc['Cash Ratio']

count   340.000
mean     70.024
std      90.421
min       0.000
25%      18.000
50%      47.000
75%      99.000
max     958.000
Name: Cash Ratio, dtype: float64


data['Cash Ratio'].mode()

0    99
dtype: int64


# Visualize histogram & boxplot for Net Cash Flow.

histogram_boxplot(data=data, feature='Net Cash Flow')


# Display the statistical summary for net cash flow.

data.describe().T.loc['Net Cash Flow']

count            340.000
mean        55537620.588
std       1946365312.176
min     -11208000000.000
25%       -193906500.000
50%          2098000.000
75%        169810750.000
max      20764000000.000
Name: Net Cash Flow, dtype: float64


# Visualize histogram & boxplot for Net Income.

histogram_boxplot(data=data, feature='Net Income')


# Display the statistical summary for net income.

data.describe().T.loc['Net Income']

count            340.000
mean      1494384602.941
std       3940150279.328
min     -23528000000.000
25%        352301250.000
50%        707336000.000
75%       1899000000.000
max      24442000000.000
Name: Net Income, dtype: float64


# Visualize histogram & boxplot for Earnings Per Share.

histogram_boxplot(data=data, feature='Earnings Per Share')


# Display the statistical summary for earnings per share.

data.describe().T.loc['Earnings Per Share']

count   340.000
mean      2.777
std       6.588
min     -61.200
25%       1.558
50%       2.895
75%       4.620
max      50.090
Name: Earnings Per Share, dtype: float64


# Visualize histogram & boxplot for Estimated Shares Outstanding.

histogram_boxplot(data=data, feature='Estimated Shares Outstanding')


# Display the statistical summary for estimated shares outstanding.

data.describe().T.loc['Estimated Shares Outstanding']

count          340.000
mean     577028337.754
std      845849595.418
min       27672156.860
25%      158848216.100
50%      309675137.800
75%      573117457.325
max     6159292035.000
Name: Estimated Shares Outstanding, dtype: float64


# Visualize histogram & boxplot for P/E Ratio.

histogram_boxplot(data=data, feature='P/E Ratio')


# Display the statistical summary for P/E ratio.

data.describe().T.loc['P/E Ratio']

count   340.000
mean     32.613
std      44.349
min       2.935
25%      15.045
50%      20.820
75%      31.765
max     528.039
Name: P/E Ratio, dtype: float64


# Visualize histogram & boxplot for P/B Ratio.

histogram_boxplot(data=data, feature='P/B Ratio')


# Display the statistical summary for P/B ratio.

data.describe().T.loc['P/B Ratio']

count   340.000
mean     -1.718
std      13.967
min     -76.119
25%      -4.352
50%      -1.067
75%       3.917
max     129.065
Name: P/B Ratio, dtype: float64


# Use a barplot to visualize the average current stock price across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='Current Price', 
            order=data.groupby(['GICS Sector'])['Current Price'].mean().reset_index().sort_values('Current Price')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average stock price for each sector.

data.groupby(['GICS Sector'])['Current Price'].mean().sort_values(ascending=False)

GICS Sector
Health Care                   132.048
Consumer Discretionary        128.095
Real Estate                    90.977
Materials                      76.552
Industrials                    74.412
Consumer Staples               71.973
Information Technology         63.548
Financials                     58.659
Utilities                      52.969
Energy                         46.042
Telecommunications Services    32.964
Name: Current Price, dtype: float64


# Use a barplot to visualize the average volatility across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='Volatility', 
            order=data.groupby(['GICS Sector'])['Volatility'].mean().reset_index().sort_values('Volatility')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average volatility for each sector.

data.groupby(['GICS Sector'])['Volatility'].mean().sort_values(ascending=False)

GICS Sector
Energy                        2.569
Materials                     1.817
Information Technology        1.660
Consumer Discretionary        1.595
Health Care                   1.541
Industrials                   1.417
Telecommunications Services   1.342
Financials                    1.267
Real Estate                   1.206
Consumer Staples              1.153
Utilities                     1.118
Name: Volatility, dtype: float64


# Use a barplot to visualize the average ROE across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='ROE', 
            order=data.groupby(['GICS Sector'])['ROE'].mean().reset_index().sort_values('ROE')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average ROE for each sector.

data.groupby(['GICS Sector'])['ROE'].mean().sort_values(ascending=False)

GICS Sector
Energy                        93.200
Consumer Staples              89.421
Industrials                   50.151
Consumer Discretionary        44.900
Materials                     33.000
Telecommunications Services   32.600
Health Care                   27.775
Financials                    26.286
Information Technology        21.788
Real Estate                   12.444
Utilities                      9.875
Name: ROE, dtype: float64


# Use a barplot to visualize the average net cash flow across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='Net Cash Flow', 
            order=data.groupby(['GICS Sector'])['Net Cash Flow'].mean().reset_index().sort_values('Net Cash Flow')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average net cash flow for each sector.

data.groupby(['GICS Sector'])['Net Cash Flow'].mean().sort_values(ascending=False)

GICS Sector
Information Technology          483099121.212
Health Care                     262687800.000
Consumer Staples                258627210.526
Financials                      254356306.122
Utilities                       176462291.667
Consumer Discretionary           84213175.000
Real Estate                       3546703.704
Industrials                    -160103150.943
Materials                      -291236850.000
Energy                         -308318233.333
Telecommunications Services   -1816800000.000
Name: Net Cash Flow, dtype: float64


# Use a barplot to visualize the average net income across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='Net Income', 
            order=data.groupby(['GICS Sector'])['Net Income'].mean().reset_index().sort_values('Net Income')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average net income for each sector.

data.groupby(['GICS Sector'])['Net Income'].mean().sort_values(ascending=False)

GICS Sector
Telecommunications Services    7067800000.000
Financials                     3202677979.592
Consumer Staples               2518833052.632
Health Care                    2018515350.000
Industrials                    1722373113.208
Information Technology         1701587272.727
Consumer Discretionary         1373450075.000
Utilities                      1107145541.667
Real Estate                     567775740.741
Materials                       278516500.000
Energy                        -2087527466.667
Name: Net Income, dtype: float64


# Use a barplot to visualize the average earnings per share across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='Earnings Per Share', 
            order=data.groupby(['GICS Sector'])['Earnings Per Share'].mean().reset_index().sort_values('Earnings Per Share')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average earnings per share for each sector.

data.groupby(['GICS Sector'])['Earnings Per Share'].mean().sort_values(ascending=False)

GICS Sector
Health Care                    4.541
Consumer Discretionary         4.526
Industrials                    4.457
Financials                     4.220
Telecommunications Services    3.550
Consumer Staples               3.224
Materials                      3.129
Utilities                      2.753
Real Estate                    2.340
Information Technology         2.266
Energy                        -6.908
Name: Earnings Per Share, dtype: float64


# Use a barplot to visualize the average estimated shares outstanding across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='Estimated Shares Outstanding', 
            order=data.groupby(['GICS Sector'])['Estimated Shares Outstanding'].mean().reset_index().sort_values('Estimated Shares Outstanding')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average estimated shares outstanding for each sector.

data.groupby(['GICS Sector'])['Estimated Shares Outstanding'].mean().sort_values(ascending=False)

GICS Sector
Telecommunications Services   2259575293.520
Consumer Staples               913685176.711
Information Technology         828278930.792
Health Care                    684595513.887
Financials                     683877334.853
Energy                         663528783.071
Consumer Discretionary         399651258.324
Utilities                      380919306.562
Industrials                    354716946.844
Real Estate                    344454019.890
Materials                      308524571.474
Name: Estimated Shares Outstanding, dtype: float64


# Use a barplot to visualize the average P/B ratio across different economic sectors.

plt.figure(figsize=(18, 5))
sns.barplot(data=data, x='GICS Sector', y='P/B Ratio', 
            order=data.groupby(['GICS Sector'])['P/B Ratio'].mean().reset_index().sort_values('P/B Ratio')['GICS Sector'].tolist())
plt.xticks(rotation=20);


# Use .groupby() function to display the average P/B ratio for each sector.

data.groupby(['GICS Sector'])['P/B Ratio'].mean().sort_values(ascending=False)

GICS Sector
Information Technology          6.377
Energy                          2.540
Materials                       0.723
Health Care                     0.069
Industrials                    -0.979
Real Estate                    -3.003
Utilities                      -3.087
Financials                     -4.271
Consumer Staples               -4.554
Consumer Discretionary         -8.254
Telecommunications Services   -11.010
Name: P/B Ratio, dtype: float64


# Use boxplot to visualize outliers.

numeric_columns = data.select_dtypes(include=np.number).columns.tolist()

plt.figure(figsize=(15, 12))

for i, variable in enumerate(numeric_columns):
    plt.subplot(4, 4, i + 1)
    plt.boxplot(data[variable], whis=1.5)
    plt.tight_layout()
    plt.title(variable)

plt.show()


# Scale the data using z-score so that features of higher magnitude are not disproprotionally weighted in the clustering models.

num_col = data.select_dtypes(include=np.number).columns.tolist()
scaler = StandardScaler()
subset = data[num_col].copy()
subset_scaled = scaler.fit_transform(subset)


# Create a DataFrame from the scaled data.

subset_scaled_df = pd.DataFrame(subset_scaled, columns=subset.columns)
subset_scaled_df.sample(5)


# Use a for loop to plot the error for each possible value of k (number of clusters).

clusters = range(2, 10)
meanDistortions = []

for k in clusters:
    model = KMeans(n_clusters=k)
    model.fit(subset_scaled_df)
    prediction = model.predict(subset_scaled_df)
    distortion = (
        sum(
            np.min(cdist(subset_scaled_df, model.cluster_centers_, "euclidean"), axis=1)
        )
        / subset_scaled_df.shape[0]
    )

    meanDistortions.append(distortion)

    print("Number of Clusters:", k, "\tAverage Distortion:", distortion)

plt.plot(clusters, meanDistortions, "bx-")
plt.xlabel("k")
plt.ylabel("Average Distortion")
plt.title("Selecting k with the Elbow Method", fontsize=20);

Number of Clusters: 2 	Average Distortion: 2.382318498894466
Number of Clusters: 3 	Average Distortion: 2.2692367155390745
Number of Clusters: 4 	Average Distortion: 2.1745559827866363
Number of Clusters: 5 	Average Distortion: 2.1132726257719026
Number of Clusters: 6 	Average Distortion: 2.0619418051649574
Number of Clusters: 7 	Average Distortion: 2.0237293529159226
Number of Clusters: 8 	Average Distortion: 1.993994405876358
Number of Clusters: 9 	Average Distortion: 1.9270632295762185


# Visualize silhouette scores to help determine the best value of k.

sil_score = []
cluster_list = list(range(2, 10))
for n_clusters in cluster_list:
    clusterer = KMeans(n_clusters=n_clusters)
    preds = clusterer.fit_predict((subset_scaled_df))
    # centers = clusterer.cluster_centers_
    score = silhouette_score(subset_scaled_df, preds)
    sil_score.append(score)
    print("For n_clusters = {}, silhouette score is {}".format(n_clusters, score))

plt.plot(cluster_list, sil_score);

For n_clusters = 2, silhouette score is 0.43969639509980457
For n_clusters = 3, silhouette score is 0.45797710447228496
For n_clusters = 4, silhouette score is 0.45434371948348606
For n_clusters = 5, silhouette score is 0.3536294114640298
For n_clusters = 6, silhouette score is 0.42153070977646057
For n_clusters = 7, silhouette score is 0.4103391826247439
For n_clusters = 8, silhouette score is 0.4089925983528137
For n_clusters = 9, silhouette score is 0.1384848848850714


# Use silhouette visualizer for more insight into the best value of k.

visualizer = SilhouetteVisualizer(KMeans(4, random_state=1))
visualizer.fit(subset_scaled_df)
visualizer.show();


# Check the silhouette scores in each cluster for the model where k=6.

visualizer = SilhouetteVisualizer(KMeans(6, random_state=1))
visualizer.fit(subset_scaled_df)
visualizer.show();


# Fit the final K-means model with k=4.

kmeans = KMeans(n_clusters=4, random_state=0)
kmeans.fit(subset_scaled_df)

KMeans(n_clusters=4, random_state=0)


# Make copies of the original and scaled DataFrames to which cluster labels will be added.

og_data = data.copy()
scaled_data = subset_scaled_df.copy()


# Add K-means cluster labels to the original and scaled DataFrames.

og_data["K_means_segments"] = kmeans.labels_
scaled_data["K_means_segments"] = kmeans.labels_


# Use groupby function to display cluster profiles.

cluster_profile = og_data.groupby("K_means_segments").mean()
cluster_profile["count_in_each_segment"] = (og_data.groupby("K_means_segments")["Security"].count().values)
cluster_profile.style.highlight_max(color="lightgreen", axis=0)


# Display boxplots to compare features across clusters.

plt.figure(figsize=(20, 15))

for i, variable in enumerate(num_col):
    plt.subplot(3, 4, i + 1)
    sns.boxplot(data=og_data, x="K_means_segments", y=variable)

plt.tight_layout(pad=2.0)


# Use a barplot to visualize and compare the averages of each numeric feature across different clusters.

scaled_data.groupby("K_means_segments").mean().plot.bar(figsize=(15, 6));


# Use groupby function to see how GICS sectors are represented across the clusters.

og_data.groupby(['K_means_segments', 'GICS Sector'])['Security'].count()

K_means_segments  GICS Sector                
0                 Consumer Discretionary          6
                  Consumer Staples                1
                  Energy                          1
                  Financials                      1
                  Health Care                     9
                  Information Technology          5
                  Real Estate                     1
                  Telecommunications Services     1
1                 Energy                         22
                  Industrials                     1
                  Information Technology          3
                  Materials                       1
2                 Consumer Discretionary          1
                  Consumer Staples                1
                  Energy                          1
                  Financials                      3
                  Health Care                     2
                  Information Technology          1
                  Telecommunications Services     2
3                 Consumer Discretionary         33
                  Consumer Staples               17
                  Energy                          6
                  Financials                     45
                  Health Care                    29
                  Industrials                    52
                  Information Technology         24
                  Materials                      19
                  Real Estate                    26
                  Telecommunications Services     2
                  Utilities                      24
Name: Security, dtype: int64


hc_data = subset_scaled_df.copy()


# Compute cophenetic correlation for various distance measures.

# list of distance metrics
distance_metrics = ["euclidean", "chebyshev", "mahalanobis", "cityblock"]

# list of linkage methods
linkage_methods = ["single", "complete", "average", "weighted"]

high_cophenet_corr = 0
high_dm_lm = [0, 0]

for dm in distance_metrics:
    for lm in linkage_methods:
        Z = linkage(hc_data, metric=dm, method=lm)
        c, coph_dists = cophenet(Z, pdist(hc_data))
        print(
            "Cophenetic correlation for {} distance and {} linkage is {}.".format(
                dm.capitalize(), lm, c
            )
        )
        if high_cophenet_corr < c:
            high_cophenet_corr = c
            high_dm_lm[0] = dm
            high_dm_lm[1] = lm

Cophenetic correlation for Euclidean distance and single linkage is 0.9232271494002922.
Cophenetic correlation for Euclidean distance and complete linkage is 0.7873280186580672.
Cophenetic correlation for Euclidean distance and average linkage is 0.9422540609560814.
Cophenetic correlation for Euclidean distance and weighted linkage is 0.8693784298129404.
Cophenetic correlation for Chebyshev distance and single linkage is 0.9062538164750717.
Cophenetic correlation for Chebyshev distance and complete linkage is 0.598891419111242.
Cophenetic correlation for Chebyshev distance and average linkage is 0.9338265528030499.
Cophenetic correlation for Chebyshev distance and weighted linkage is 0.9127355892367.
Cophenetic correlation for Mahalanobis distance and single linkage is 0.925919553052459.
Cophenetic correlation for Mahalanobis distance and complete linkage is 0.7925307202850002.
Cophenetic correlation for Mahalanobis distance and average linkage is 0.9247324030159736.
Cophenetic correlation for Mahalanobis distance and weighted linkage is 0.8708317490180428.
Cophenetic correlation for Cityblock distance and single linkage is 0.9334186366528574.
Cophenetic correlation for Cityblock distance and complete linkage is 0.7375328863205818.
Cophenetic correlation for Cityblock distance and average linkage is 0.9302145048594667.
Cophenetic correlation for Cityblock distance and weighted linkage is 0.731045513520281.


# Print the combination of distance metric and linkage method with the highest cophenetic correlation.

print("Highest cophenetic correlation is {}, which is obtained with {} distance and {} linkage.".format(
        high_cophenet_corr, high_dm_lm[0].capitalize(), high_dm_lm[1]))

Highest cophenetic correlation is 0.9422540609560814, which is obtained with Euclidean distance and average linkage.


# Explore different linkage methods with Euclidean distance.

linkage_methods = ["single", "complete", "average", "centroid", "ward", "weighted"]

high_cophenet_corr = 0
high_dm_lm = [0, 0]

for lm in linkage_methods:
    Z = linkage(hc_data, metric="euclidean", method=lm)
    c, coph_dists = cophenet(Z, pdist(hc_data))
    print("Cophenetic correlation for {} linkage is {}.".format(lm, c))
    if high_cophenet_corr < c:
        high_cophenet_corr = c
        high_dm_lm[0] = "euclidean"
        high_dm_lm[1] = lm

Cophenetic correlation for single linkage is 0.9232271494002922.
Cophenetic correlation for complete linkage is 0.7873280186580672.
Cophenetic correlation for average linkage is 0.9422540609560814.
Cophenetic correlation for centroid linkage is 0.9314012446828154.
Cophenetic correlation for ward linkage is 0.7101180299865353.
Cophenetic correlation for weighted linkage is 0.8693784298129404.


# Print the combination of distance metric and linkage method with the highest cophenetic correlation.

print("Highest cophenetic correlation is {}, which is obtained with {} linkage.".format(
        high_cophenet_corr, high_dm_lm[1]))

Highest cophenetic correlation is 0.9422540609560814, which is obtained with average linkage.


# Visualize dendrograms for various linkage methods.

# list of linkage methods
linkage_methods = ["single", "complete", "average", "centroid", "ward", "weighted"]

# lists to save results of cophenetic correlation calculation
compare_cols = ["Linkage", "Cophenetic Coefficient"]

# Create a subplot image
fig, axs = plt.subplots(len(linkage_methods), 1, figsize=(15, 30))

# Enumerate through the list of linkage methods above, plot the dendrogram and calculate the cophenetic correlation
for i, method in enumerate(linkage_methods):
    Z = linkage(hc_data, metric="euclidean", method=method)

    dendrogram(Z, ax=axs[i])
    axs[i].set_title(f"Dendrogram ({method.capitalize()} Linkage)")

    coph_corr, coph_dist = cophenet(Z, pdist(hc_data))
    axs[i].annotate(
        f"Cophenetic\nCorrelation\n{coph_corr:0.2f}",
        (0.80, 0.80),
        xycoords="axes fraction",
    )


# Build the hierarchical clustering model.

HCmodel = AgglomerativeClustering(n_clusters=4, affinity="euclidean", linkage="average")
HCmodel.fit(hc_data)

AgglomerativeClustering(linkage='average', n_clusters=4)


# Make a copy of the original (un-scaled) data to add hierarchical clustering labels.
og_hc_data = data.copy()

hc_data['HC_Clusters'] = HCmodel.labels_
og_hc_data['HC_Clusters'] = HCmodel.labels_


# Use groupby function to display cluster profiles.

cluster_profile_hc = og_hc_data.groupby("HC_Clusters").mean()
cluster_profile_hc["count_in_each_segment"] = (og_hc_data.groupby("HC_Clusters")["Security"].count().values)
cluster_profile_hc.style.highlight_max(color="lightgreen", axis=0)


# Display boxplots to compare features across clusters.

plt.figure(figsize=(20, 15))

for i, variable in enumerate(num_col):
    plt.subplot(3, 4, i + 1)
    sns.boxplot(data=og_hc_data, x="HC_Clusters", y=variable)

plt.tight_layout(pad=2.0)


# Use a barplot to visualize and compare the averages of each numeric feature across different clusters.

hc_data.groupby("HC_Clusters").mean().plot.bar(figsize=(15, 6));


# Use groupby function to see how GICS sectors are represented across the clusters.

og_hc_data.groupby(['HC_Clusters', 'GICS Sector'])['Security'].count()

HC_Clusters  GICS Sector                
0            Consumer Discretionary         39
             Consumer Staples               19
             Energy                         28
             Financials                     49
             Health Care                    40
             Industrials                    53
             Information Technology         32
             Materials                      20
             Real Estate                    27
             Telecommunications Services     5
             Utilities                      24
1            Consumer Discretionary          1
2            Energy                          2
3            Information Technology          1
Name: Security, dtype: int64

	count	mean	std	min	25%	50%	75%	max
order_id	1898.00	1477495.50	548.05	1476547.00	1477021.25	1477495.50	1477969.75	1478444.00
customer_id	1898.00	171168.48	113698.14	1311.00	77787.75	128600.00	270525.00	405334.00
cost_of_the_order	1898.00	16.50	7.48	4.47	12.08	14.14	22.30	35.41
food_preparation_time	1898.00	27.37	4.63	20.00	23.00	27.00	31.00	35.00
delivery_time	1898.00	24.16	4.97	15.00	20.00	25.00	28.00	33.00

	Actual Values	Fitted Values	Residuals
3026	4.09	3.87	0.22
1525	4.45	4.60	-0.15
1128	4.32	4.29	0.03
3003	4.28	4.19	0.09
2907	4.46	4.49	-0.03

	Odds	% change
arrival_year	1.57324	57.32351
type_of_meal_plan_Not Selected	1.33089	33.08924
no_of_previous_cancellations	1.25716	25.71567
type_of_meal_plan_Meal Plan 2	1.17992	17.99156
no_of_children	1.16436	16.43601
no_of_adults	1.11475	11.47536
no_of_weekend_nights	1.11475	11.47526
no_of_week_nights	1.04264	4.26363
avg_price_per_room	1.01935	1.93479
lead_time	1.01584	1.58352
arrival_month	0.95853	-4.14725
room_type_reserved_Room_Type 4	0.75383	-24.61701
room_type_reserved_Room_Type 2	0.70046	-29.95389
room_type_reserved_Room_Type 5	0.47940	-52.05967
market_segment_type_Corporate	0.45258	-54.74162
room_type_reserved_Room_Type 6	0.38099	-61.90093
room_type_reserved_Room_Type 7	0.23903	-76.09669
no_of_special_requests	0.22994	-77.00595
required_car_parking_space	0.20305	-79.69523
market_segment_type_Offline	0.16750	-83.24963
repeated_guest	0.06480	-93.52026
const	0.00000	-100.00000

	Logistic Regression statsmodel	Logistic Regression-0.37 Threshold	Logistic Regression-0.42 Threshold
Accuracy	0.80541	0.79289	0.80128
Recall	0.63255	0.73562	0.69939
Precision	0.73903	0.66870	0.69789
F1	0.68166	0.70056	0.69864

	Logistic Regression statsmodel	Logistic Regression-0.37 Threshold	Logistic Regression-0.42 Threshold
Accuracy	0.80465	0.79601	0.80364
Recall	0.63089	0.73935	0.70386
Precision	0.72900	0.66667	0.69381
F1	0.67641	0.70113	0.69880

	order_id	customer_id	restaurant_name	cuisine_type	cost_of_the_order	day_of_the_week	rating	food_preparation_time	delivery_time
0	1477147	337525	Hangawi	Korean	30.75	Weekend	Not given	25	20
1	1477685	358141	Blue Ribbon Sushi Izakaya	Japanese	12.08	Weekend	Not given	25	23
2	1477070	66393	Cafe Habana	Mexican	12.23	Weekday	5	23	28
3	1477334	106968	Blue Ribbon Fried Chicken	American	29.20	Weekend	3	25	15
4	1478249	76942	Dirty Bird to Go	American	11.59	Weekday	4	25	24

	restaurant_name	mean	count
0	'wichcraft	5.00	1
1	12 Chairs	4.50	2
2	5 Napkin Burger	4.00	2
3	67 Burger	5.00	1
4	Amma	4.50	2
...	...	...	...
151	Zero Otto Nove	4.00	1
152	brgr	3.00	1
153	da Umberto	5.00	1
154	ilili Restaurant	4.15	13
155	indikitch	4.50	2

	user_id	group	landing_page	time_spent_on_the_page	converted	language_preferred
0	546592	control	old	3.48	no	Spanish
1	546468	treatment	new	7.13	yes	English
2	546462	treatment	new	4.40	no	Spanish
3	546567	control	old	3.02	no	French
4	546459	treatment	new	4.75	yes	Spanish
...	...	...	...	...	...	...
95	546446	treatment	new	5.15	no	Spanish
96	546544	control	old	6.52	yes	English
97	546472	treatment	new	7.07	yes	Spanish
98	546481	treatment	new	6.20	yes	Spanish
99	546483	treatment	new	5.86	yes	English

	count	unique	top	freq
group	100	2	control	50
landing_page	100	2	old	50
converted	100	2	yes	54
language_preferred	100	3	Spanish	34

	brand_name	os	screen_size	4g	5g	main_camera_mp	selfie_camera_mp	int_memory	ram	battery	weight	release_year	days_used	normalized_used_price	normalized_new_price
472	Alcatel	Android	15.24	yes	no	8.00	5.00	16.00	4.00	3000.00	155.00	2018	586	3.95	5.07
719	Asus	Android	18.01	yes	no	13.00	5.00	64.00	4.00	4680.00	168.00	2017	847	4.84	5.70
1719	LG	Android	12.70	no	no	8.00	1.00	32.00	4.00	2540.00	137.00	2014	646	3.82	4.62
696	Others	Android	10.29	yes	no	5.00	0.30	16.00	4.00	1850.00	140.00	2014	691	3.82	5.44
1358	Huawei	Android	17.78	yes	no	13.00	5.00	16.00	4.00	5000.00	239.00	2015	700	4.59	5.92

	count	mean	std	min	25%	50%	75%	max
screen_size	3454.00	13.71	3.81	5.08	12.70	12.83	15.34	30.71
main_camera_mp	3275.00	9.46	4.82	0.08	5.00	8.00	13.00	48.00
selfie_camera_mp	3452.00	6.55	6.97	0.00	2.00	5.00	8.00	32.00
int_memory	3450.00	54.57	84.97	0.01	16.00	32.00	64.00	1024.00
ram	3450.00	4.04	1.37	0.02	4.00	4.00	4.00	12.00
battery	3448.00	3133.40	1299.68	500.00	2100.00	3000.00	4000.00	9720.00
weight	3447.00	182.75	88.41	69.00	142.00	160.00	185.00	855.00
days_used	3454.00	674.87	248.58	91.00	533.50	690.50	868.75	1094.00
normalized_used_price	3454.00	4.36	0.59	1.54	4.03	4.41	4.76	6.62
normalized_new_price	3454.00	5.23	0.68	2.90	4.79	5.25	5.67	7.85

	count	unique	top	freq
brand_name	3454	34	Others	502
os	3454	4	Android	3214
4g	3454	2	yes	2335
5g	3454	2	no	3302

	Count	Percentage
main_camera_mp	179	5.18
selfie_camera_mp	2	0.06
int_memory	4	0.12
ram	4	0.12
battery	6	0.17
weight	7	0.20

	brand_name	os	screen_size	4g	5g	main_camera_mp	selfie_camera_mp	int_memory	ram	battery	weight	release_year	days_used	normalized_used_price	normalized_new_price
59	Infinix	Android	17.32	yes	no	NaN	8.00	32.00	2.00	6000.00	209.00	2020	245	4.28	4.60
60	Infinix	Android	15.39	yes	no	NaN	8.00	64.00	4.00	5000.00	185.00	2020	173	4.36	4.71
61	Infinix	Android	15.39	yes	no	NaN	8.00	32.00	2.00	5000.00	185.00	2020	256	4.18	4.51
62	Infinix	Android	15.39	yes	no	NaN	16.00	32.00	3.00	4000.00	178.00	2019	316	4.56	4.60
63	Infinix	Android	15.29	yes	no	NaN	16.00	32.00	2.00	4000.00	165.00	2019	468	4.42	4.87
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
3411	Realme	Android	15.34	yes	no	NaN	16.00	64.00	4.00	4000.00	183.00	2019	503	4.57	5.16
3412	Realme	Android	15.32	yes	no	NaN	16.00	64.00	4.00	4035.00	184.00	2019	433	4.52	5.07
3413	Realme	Android	15.32	yes	no	NaN	25.00	64.00	4.00	4045.00	172.00	2019	288	4.78	4.97
3448	Asus	Android	16.74	yes	no	NaN	24.00	128.00	8.00	6000.00	240.00	2019	325	5.72	7.06
3449	Asus	Android	15.34	yes	no	NaN	8.00	64.00	6.00	5000.00	190.00	2019	232	4.49	6.48

	count	mean	std	min	25%	50%	75%	max
main_camera_mp	1.05	1.02	0.99	1.00	1.00	1.01	1.00	1.00
selfie_camera_mp	1.00	1.00	1.00	NaN	1.00	1.00	1.00	1.00
int_memory	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00
ram	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00
battery	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00
weight	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00

	count	mean	std	25%	50%	75%	max
no_of_adults	36275.0	1.844962	0.518715	2.0	2.00	2.0	4.0
no_of_children	36275.0	0.105279	0.402648	0.0	0.00	0.0	10.0
no_of_weekend_nights	36275.0	0.810724	0.870644	0.0	1.00	2.0	7.0
no_of_week_nights	36275.0	2.204300	1.410905	1.0	2.00	3.0	17.0
lead_time	36275.0	85.232557	85.930817	17.0	57.00	126.0	443.0
no_of_previous_cancellations	36275.0	0.023349	0.368331	0.0	0.00	0.0	13.0
no_of_previous_bookings_not_canceled	36275.0	0.153411	1.754171	0.0	0.00	0.0	58.0
avg_price_per_room	36275.0	103.423539	35.089424	80.3	99.45	120.0	540.0
no_of_special_requests	36275.0	0.619655	0.786236	0.0	0.00	1.0	5.0

	const	screen_size	main_camera_mp	selfie_camera_mp	int_memory	ram	battery	weight	days_used	normalized_new_price	...	4g_yes	5g_yes
0	1.00	14.50	13.00	5.00	64.00	3.00	3020.00	146.00	127	4.72	...	1	0
1	1.00	17.30	13.00	16.00	128.00	8.00	4300.00	213.00	325	5.52	...	1	1
2	1.00	16.69	13.00	8.00	128.00	8.00	4200.00	213.00	162	5.88	...	1	1
3	1.00	25.50	13.00	8.00	64.00	6.00	7250.00	480.00	345	5.63	...	1	1
4	1.00	15.32	13.00	8.00	64.00	3.00	5000.00	185.00	293	4.95	...	1	0

	feature	VIF
0	const	233.24
1	screen_size	7.68
7	weight	6.40
12	brand_name_Apple	13.06
21	brand_name_Huawei	5.98
34	brand_name_Others	9.71
37	brand_name_Samsung	7.54
46	os_iOS	11.78

	feature	VIF
0	const	206.34
11	brand_name_Apple	13.00
20	brand_name_Huawei	5.98
33	brand_name_Others	9.65
36	brand_name_Samsung	7.52
45	os_iOS	11.68

	Booking_ID	no_of_adults	no_of_weekend_nights	no_of_week_nights	type_of_meal_plan	room_type_reserved	lead_time	arrival_year	arrival_month	arrival_date	market_segment_type	avg_price_per_room	no_of_special_requests	booking_status
22995	INN22996	2	1	4	Meal Plan 1	Room_Type 1	141	2018	5	30	Online	99.96	0	Canceled
10065	INN10066	1	1	0	Meal Plan 1	Room_Type 1	77	2018	10	30	Online	85.50	2	Not_Canceled
14837	INN14838	1	0	1	Meal Plan 1	Room_Type 4	1	2018	2	17	Online	66.30	1	Not_Canceled
8360	INN08361	2	0	3	Meal Plan 1	Room_Type 5	11	2017	12	29	Offline	157.67	0	Not_Canceled
23229	INN23230	2	2	2	Meal Plan 1	Room_Type 1	76	2018	4	10	Online	90.95	1	Not_Canceled

	count	unique	top	freq
type_of_meal_plan	36275	4	Meal Plan 1	27835
room_type_reserved	36275	7	Room_Type 1	28130
market_segment_type	36275	5	Online	23214
booking_status	36275	2	Not_Canceled	24390

	ccp_alphas	impurities
0	0.00000	0.00838
1	-0.00000	0.00838
2	0.00000	0.00838
3	0.00000	0.00838
4	0.00000	0.00838
...	...	...
1837	0.00890	0.32806
1838	0.00980	0.33786
1839	0.01272	0.35058
1840	0.03412	0.41882
1841	0.08118	0.50000

	Decision Tree without pruning	Decision Tree (Pre-Pruning)	Decision Tree (Post-Pruning)
Accuracy	0.99421	0.83101	0.90005
Recall	0.98661	0.78620	0.90350
Precision	0.99578	0.72428	0.81361
F1	0.99117	0.75397	0.85620

	Decision Tree without pruning	Decision Tree (Pre-Pruning)	Decision Tree (Post-Pruning)
Accuracy	0.87108	0.83497	0.86869
Recall	0.81034	0.78336	0.85576
Precision	0.79521	0.72758	0.76595
F1	0.80270	0.75444	0.80837

	case_id	continent	education_of_employee	has_job_experience	requires_job_training	no_of_employees	yr_of_estab	region_of_employment	prevailing_wage	unit_of_wage	full_time_position	case_status
19030	EZYV19031	Asia	Bachelor's	N	N	1001	1998	Northeast	53177.380	Year	Y	Certified
9736	EZYV9737	Asia	Bachelor's	N	N	1627	2011	Northeast	50743.320	Year	Y	Denied
5987	EZYV5988	Asia	Master's	Y	N	2690	2007	West	85269.340	Year	Y	Certified
22181	EZYV22182	Asia	Master's	N	N	3120	1908	Northeast	145360.140	Year	N	Certified
20478	EZYV20479	Asia	Bachelor's	N	N	1695	2005	South	56755.660	Year	Y	Certified

	count	mean	std	min	25%	50%	75%	max
no_of_employees	25480.000	5667.043	22877.929	-26.000	1022.000	2109.000	3504.000	602069.000
prevailing_wage	25480.000	74455.815	52815.942	2.137	34015.480	70308.210	107735.513	319210.270
yrs_since_estab	25480.000	42.590	42.367	6.000	17.000	25.000	46.000	222.000

Project Python Foundations: FoodHub Data Analysis¶

Context¶

Objective¶

Data Description¶

Data Dictionary¶

Let us start by importing the required libraries¶

Understanding the structure of the data¶

Observations:¶

Question 1: How many rows and columns are present in the data? [0.5 mark]¶

Observations:¶

Question 2: What are the datatypes of the different columns in the dataset? (The info() function can be used) [0.5 mark]¶

Observations:¶

Question 3: Are there any missing values in the data? If yes, treat them using an appropriate method. [1 mark]¶

Observations:¶

Question 4: Check the statistical summary of the data. What is the minimum, average, and maximum time it takes for food to be prepared once an order is placed? [2 marks]¶

Observations:¶

Question 5: How many orders are not rated? [1 mark]¶

Observations:¶

Exploratory Data Analysis (EDA)¶

Univariate Analysis¶

Question 6: Explore all the variables and provide observations on their distributions. (Generally, histograms, boxplots, countplots, etc. are used for univariate exploration.) [9 marks]¶

Question 7: Which are the top 5 restaurants in terms of the number of orders received? [1 mark]¶

Observations:¶

Question 8: Which is the most popular cuisine on weekends? [1 mark]¶

Observations:¶

Question 9: What percentage of the orders cost more than 20 dollars? [2 marks]¶

Observations:¶

Question 10: What is the mean order delivery time? [1 mark]¶

Observations:¶

Question 11: The company has decided to give 20% discount vouchers to the top 3 most frequent customers. Find the IDs of these customers and the number of orders they placed. [1 mark]¶

Observations:¶

Multivariate Analysis¶

Question 12: Perform a multivariate analysis to explore relationships between the important variables in the dataset. (It is a good idea to explore relations between numerical variables as well as relations between numerical and categorical variables) [10 marks]¶

Observations:¶

Question 14: The company charges the restaurant 25% on the orders having cost greater than 20 dollars and 15% on the orders having cost greater than 5 dollars. Find the net revenue generated by the company across all orders. [3 marks]¶

Observations: The net revenue is $6166.30¶

Question 15: The company wants to analyze the total time required to deliver the food. What percentage of orders take more than 60 minutes to get delivered from the time the order is placed? (The food has to be prepared and then delivered.) [2 marks]¶

Observations:¶

Question 16: The company wants to analyze the delivery time of the orders on weekdays and weekends. How does the mean delivery time vary during weekdays and weekends? [2 marks]¶

Observations:¶

Conclusion and Recommendations¶

Question 17: What are your conclusions from the analysis? What recommendations would you like to share to help improve the business? (You can use cuisine type and feedback ratings to drive your business recommendations.) [6 marks]¶

Conclusions:¶

Recommendations:¶

Project Business Statistics: E-news Express¶

Define Problem Statement and Objectives¶

Import all the necessary libraries¶

Reading the Data into a DataFrame¶

Explore the dataset and extract insights using Exploratory Data Analysis¶

Univariate Analysis¶

Bivariate Analysis¶

1. Do the users spend more time on the new landing page than the existing landing page?¶

Perform Visual Analysis¶

Step 1: Define the null and alternate hypotheses¶

Step 2: Select Appropriate test¶

Step 3: Decide the significance level¶

Step 4: Collect and prepare data¶

Step 5: Calculate the p-value¶

Step 6: Compare the p-value with $\alpha$¶

Step 7: Draw inference¶

2. Is the conversion rate (the proportion of users who visit the landing page and get converted) for the new page greater than the conversion rate for the old page?¶

3. Is the conversion and preferred language are independent or related?¶

4. Is the time spent on the new page same for the different language users?¶

Conclusion and Business Recommendations¶

Supervised Learning - Foundations Project: ReCell¶

Problem Statement¶

Business Context¶

Objective¶

Data Description¶

Importing necessary libraries¶

Loading the dataset¶

Data Overview¶

Exploratory Data Analysis (EDA)¶

Questions¶

Further analysis¶

Univariate analysis¶

Data Preprocessing¶

Missing value treatment¶

Feature engineering¶

Outlier detection & treatment¶

	region	certified	total	pct_cert
0	Midwest	3253	4307	75.528
1	South	4913	7017	70.016
2	Northeast	4526	7195	62.905
3	West	4100	6586	62.253
4	Island	226	375	60.267

	education level	certified	total	pct_cert
0	Doctorate	1912	2192	87.226
1	Master's	7575	9634	78.628
2	Bachelor's	6367	10234	62.214
3	High School	1164	3420	34.035

	continent	certified	total	pct_cert
0	Europe	2957	3732	79.234
1	Africa	397	551	72.051
2	Asia	11012	16861	65.310
3	Oceania	122	192	63.542
4	North America	2037	3292	61.877
5	South America	493	852	57.864

	unit of wage	certified	total	pct_cert
0	Year	16047	22962	69.885
1	Week	169	272	62.132
2	Month	55	89	61.798
3	Hour	747	2157	34.631

	Decision Tree	Decision Tree Estimator	Random Forest	Random Forest Tuned	Bagging Classifier	Bagging Estimator Tuned	Adaboost Classifier	Adaboost Classifier Tuned	Gradient Boost Classifier	Gradient Boost Classifier Tuned	Stacking Classifier
Accuracy	1.000	0.668	1.000	0.823	0.985	0.668	0.738	0.718	0.759	0.765	0.788
Recall	1.000	1.000	1.000	0.928	0.986	1.000	0.887	0.936	0.883	0.886	0.900
Precision	1.000	0.668	1.000	0.828	0.992	0.668	0.760	0.723	0.784	0.789	0.806
F1	1.000	0.801	1.000	0.875	0.989	0.801	0.819	0.816	0.831	0.834	0.850

	Decision Tree	Decision Tree Estimator	Random Forest	Random Forest Tuned	Bagging Classifier	Bagging Estimator Tuned	Adaboost Classifier	Adaboost Classifier Tuned	Gradient Boost Classifier	Gradient Boost Classifier Tuned	Stacking Classifier
Accuracy	0.658	0.668	0.721	0.740	0.695	0.668	0.733	0.711	0.745	0.746	0.742
Recall	0.738	1.000	0.834	0.871	0.768	1.000	0.885	0.936	0.873	0.874	0.870
Precision	0.747	0.668	0.768	0.770	0.774	0.668	0.757	0.718	0.774	0.774	0.772
F1	0.742	0.801	0.799	0.817	0.771	0.801	0.816	0.812	0.820	0.821	0.818

	V1	V2	V3	V4	V5	V6	V7	V8	V9	V10	...	V32	V33	V34	V35	V36	V37	V38	V39	V40
24482	-1.893	1.124	2.268	-0.685	2.284	-1.943	-1.091	1.678	-1.320	-0.787	...	4.395	-0.075	-2.686	1.269	3.710	0.737	-1.864	0.879	0.911
11743	2.328	-3.935	10.720	-2.265	-4.851	-3.617	-2.130	-0.336	0.192	2.799	...	-6.279	-2.592	3.408	7.088	7.512	-0.531	-6.752	3.495	-3.322
8692	0.952	1.828	0.627	-4.590	0.951	0.336	-0.548	1.471	0.801	-5.211	...	-1.953	2.536	-6.538	-0.152	0.508	2.678	-3.713	-0.282	5.223
38184	-4.174	-2.618	-0.984	0.475	0.245	-2.189	-2.336	1.323	-0.130	-0.161	...	4.279	-1.642	0.122	1.342	2.632	2.270	-2.576	1.683	-2.760
18288	-4.586	1.305	2.605	2.192	3.607	-2.984	-3.190	3.248	-1.544	-1.143	...	14.279	5.986	-5.972	5.787	1.996	-1.161	-5.060	-0.676	-1.772

	V1	V2	V3	V4	V5	V6	V7	V8	V9	V10	...	V32	V33	V34	V35	V36	V37	V38	V39	V40
2487	6.952	1.993	4.852	-6.759	-1.345	2.574	1.228	-5.555	-0.032	2.201	...	-6.674	1.496	-2.200	2.578	3.283	-2.056	4.630	1.841	1.636
6885	-1.548	-0.392	5.059	1.832	-1.974	-1.070	-1.738	-3.859	0.513	1.291	...	-6.186	-2.628	4.300	3.235	1.953	0.701	3.427	2.833	-3.052
9453	1.397	1.853	5.400	-0.087	0.341	-5.516	1.166	5.873	-2.683	-1.162	...	0.375	-6.597	1.013	2.064	4.931	1.280	-4.513	0.509	1.979
7733	0.049	-0.642	3.362	0.730	-0.260	-1.343	-1.820	-1.911	2.322	0.751	...	-0.444	-1.977	-0.073	0.699	2.956	-0.387	-2.852	1.713	-2.355
563	-4.556	-3.610	-1.024	-1.337	-0.866	0.358	-1.687	-2.053	0.124	1.109	...	-3.390	-1.942	3.067	-1.668	3.256	2.864	1.409	3.487	-2.080

	V1	V2	V3	V4	V5	V6	V7	V8	V9	V10	...	V32	V33	V34	V35	V36	V37	V38	V39	V40	Target
count	39954.000	39961.000	40000.000	40000.000	40000.000	40000.000	40000.000	40000.000	40000.000	40000.000	...	40000.000	40000.000	40000.000	40000.000	40000.000	40000.000	40000.000	40000.000	40000.000	40000.000
mean	-0.288	0.443	2.506	-0.066	-0.045	-1.001	-0.893	-0.563	-0.008	-0.002	...	0.327	0.057	-0.464	2.235	1.530	-0.000	-0.351	0.900	-0.897	0.055
std	3.449	3.139	3.406	3.437	2.107	2.037	1.757	3.299	2.162	2.183	...	5.499	3.574	3.186	2.924	3.820	1.778	3.964	1.751	2.998	0.227
min	-13.502	-13.212	-11.469	-16.015	-8.613	-10.227	-8.206	-15.658	-8.596	-11.001	...	-23.201	-17.454	-17.985	-15.350	-17.479	-7.640	-17.375	-7.136	-11.930	0.000
25%	-2.751	-1.638	0.203	-2.350	-1.507	-2.363	-2.037	-2.660	-1.494	-1.391	...	-3.392	-2.238	-2.128	0.332	-0.937	-1.266	-3.017	-0.262	-2.950	0.000
50%	-0.774	0.464	2.265	-0.124	-0.097	-1.007	-0.935	-0.384	-0.052	0.106	...	0.056	-0.050	-0.251	2.110	1.572	-0.133	-0.319	0.921	-0.949	0.000
75%	1.837	2.538	4.585	2.149	1.346	0.374	0.207	1.714	1.426	1.486	...	3.789	2.256	1.433	4.045	3.997	1.161	2.291	2.069	1.092	0.000
max	17.437	13.089	18.366	13.280	9.403	7.065	8.006	11.679	8.507	8.108	...	24.848	16.692	14.358	16.805	19.330	7.803	15.964	7.998	10.654	1.000

	V1	V2	V3	V4	V5	V6	V7	V8	V9	V10	...	V32	V33	V34	V35	V36	V37	V38	V39	V40	Target
count	9989.000	9993.000	10000.000	10000.000	10000.000	10000.000	10000.000	10000.000	10000.000	10000.000	...	10000.000	10000.000	10000.000	10000.000	10000.000	10000.000	10000.000	10000.000	10000.000	10000.000
mean	-0.260	0.417	2.555	-0.054	-0.085	-1.014	-0.908	-0.599	0.026	0.019	...	0.253	0.008	-0.423	2.258	1.550	-0.006	-0.373	0.920	-0.937	0.055
std	3.440	3.160	3.395	3.462	2.102	2.039	1.737	3.343	2.180	2.169	...	5.503	3.552	3.168	2.919	3.794	1.782	3.998	1.726	3.011	0.227
min	-12.382	-11.625	-12.941	-14.682	-7.712	-8.949	-8.124	-12.710	-7.570	-8.291	...	-20.520	-14.904	-17.135	-19.522	-14.912	-5.362	-15.335	-7.147	-10.779	0.000
25%	-2.700	-1.701	0.238	-2.371	-1.593	-2.377	-2.035	-2.684	-1.490	-1.362	...	-3.459	-2.280	-2.066	0.375	-0.892	-1.278	-3.004	-0.225	-2.993	0.000
50%	-0.719	0.456	2.283	-0.169	-0.144	-1.015	-0.938	-0.387	-0.086	0.150	...	-0.013	-0.099	-0.203	2.149	1.620	-0.150	-0.362	0.933	-0.986	0.000
75%	1.861	2.526	4.656	2.144	1.324	0.354	0.189	1.698	1.466	1.537	...	3.762	2.198	1.472	4.088	4.061	1.193	2.335	2.097	1.085	0.000
max	13.504	14.079	15.409	12.896	7.673	6.273	7.616	10.792	8.851	7.691	...	26.539	13.324	14.581	13.489	17.116	7.682	13.726	7.234	10.392	1.000